Search the siteSearch in

Interview paths
Question bank
Coding practice
Study materials
Infrastructure lab

Community

Weekly sessions
Peer practice
Contribute

News

Jobs

Open roles
Market intelligence
Companies
Roles

Feedback

Product feedback
Developer feedback

Checking account…

Home
Question bank

Frontier AI technical interview question bank.

Practice coding, system design, behavioral, and project questions for frontier AI roles.

Company

Loading the question catalog…

Preparing this page…

Your current navigation and account state stay available while the next page loads.

Frontier Rehearsal · Independent practice · Not affiliated with OpenAI, Anthropic, or xAI.

Home Interview questions Company interview processes Company reports Role reports Market intelligence Open roles Python lab Materials How it works About Feedback Uploads Feature requests Terms Privacy 中文 English

Home
Question bank

Frontier AI technical interview question bank.

Practice coding, system design, behavioral, and project questions for frontier AI roles.

Company

FREE PRACTICE

Public demos, always pinned.

Start with either demo. They remain here when you filter or sort.

Free account: sign in to practice the marked Free questions.

Newest published questions; deterministic, never randomized.

Demo 1Number search with delayed feedback
Demo 2Design real-time device monitoring and control

Question bank filters

Reset filters

Question groups

Filter question bank by interview groupAll 83 Coding 41 System design 10 Behavioral 15 Hiring manager 10 Project deep dive 7

Topics

Filter question bank by topic tagsAll 83 Python 41 Algorithms 6 Data structures 15 Concurrency 6 Distributed systems 2 Storage & state 15 Networking 2 Reliability 15 ML / AI 12 Data / SQL 11 Product design 4 Communication 35

Independent and not affiliated with the companies represented. Collected material does not predict future interview questions.

68 questions

Sort question bankSortFree first Newest Oldest AI ratio ↓AI ratio ↑

Question bank results

Every question has a public brief with the task, constraints, and follow-ups. Labels describe interactive practice access.

Public brief

Topic tags
Python

AnthropicCoding

Talk-through codingNo local grader

Reported interview periodJun 2026–Jul 2026

Repair a Looping Instruction Program

A small virtual machine executes a list of instructions over one integer accumulator. Blank lines and comment lines are ignored.

Practice focus- plus n : add n to the accumulator and move to the next instruction. - next n : ignore n and move to the next instruction. - jump n : move to the instruction at current index + n . Execution halts when the program counter moves outside the instruction list. It loops when it is about to execute an instruction that has already run. Exactly one jump or next instruction was swapped while keeping its operand. Interface Return -1 from the first two functions if the original program already halts.…

Public brief

Topic tags
Python

AnthropicCoding

Python codingWebAssembly + public tests

Reported interview periodJan 2025–Jul 2026

Build a Bank Ledger with Held Transfers and Account Merges

Implement an in-memory banking service whose operations arrive in nondecreasing timestamp order.

Practice focusRequirements - Account creation starts at zero and returns True , or False if that identifier is already active. Deposits and withdrawals return the total balance, including held funds; invalid accounts or invalid amounts return None . A zero deposit is a read of the current balance. Negative deposits, and zero or negative withdrawals and transfers, are invalid. - Starting a transfer requires both accounts to exist and available funds (total balance minus holds) to cover the amount.…

Public brief

Topic tags
Python
ML / AI

AnthropicCoding

Python codingWebAssembly + public tests

Reported interview periodSep 2025–Jun 2026

Implement a Longest-Match Tokenizer

Given an input string and a vocabulary, tokenize from left to right using longest-prefix matching.

Practice focusAt each position, emit the integer ID of the longest vocabulary entry matching the remaining text. If nothing matches, emit vocab["UNK"] and advance by one character. With collapse unk=True , collapse consecutive unknown IDs into a single ID; otherwise emit one for each unmatched character. The literal vocabulary entry UNK is reserved and must not match input text as an ordinary token. Assume every token has a distinct integer ID and the vocabulary contains UNK . Requirements and edge cases - Return an empty list for empty input.…

Public brief

Topic tags
Python
Communication

AnthropicCoding

Python codingWebAssembly + public tests

Reported interview periodNov 2025–Jun 2026

Implement a Versioned Recipe Manager

Build an in-memory recipe service with unique names, search, users, and rollback.

Practice focusRecipe IDs and names are unique; name comparison and search are case-insensitive while original casing is preserved. Returned recipes must be defensive copies. Search results sort by ingredient count and then recipe ID. Successful adds and edits append immutable, one-based versions. IDs and names are nonempty strings; ingredients are lists of strings, preserving order and repetitions. Name uniqueness and substring search compare Python-style lowercase strings, without trimming or accent normalization. An empty search query matches every recipe.…

Public brief

Topic tags
Python

AnthropicCoding

Python codingWebAssembly + public tests

Reported interview periodSep 2025–Jun 2026

Implement a Same-Host Web Crawler

You are given a seed URL and a parser object. Calling htmlParser.getUrls(url) returns the links found on that page. Return every reachable URL whose hostname matches the seed URL's hostname, including the seed …

Practice focusRequirements - Visit each accepted URL at most once. - Never follow a link to another hostname. - Use the supplied parser rather than implementing HTTP fetching. - Return all reachable accepted URLs; result order is not significant. - Treat complete URL strings as visit identities. Compare parsed hostnames, not hostname substrings; different ports and schemes on the same hostname remain eligible. Assume syntactically valid absolute HTTP(S) URLs. No URL canonicalization, redirect fetching or network access is required.…

Public brief

Topic tags
Python
Data structures
Reliability

AnthropicCodingHalf AI-generated

Talk-through codingNo local grader

Reported interview periodOct 2025–Jun 2026

Design a Type-Safe Durable LRU Cache

Extend a crash-recoverable LRU cache to support built-in containers and explicitly registered domain objects without using unsafe object serialization.

Practice focusRequirements - Produce canonical, type-tagged keys for None , booleans, integers, finite floats, strings, bytes, lists, tuples, dictionaries, sets, frozensets, and registered objects. - Preserve distinctions such as True , 1 , and 1.0 ; make dictionary and set identity independent of iteration order. - Allowlist exact classes through unique stable tags. Never dynamically import a class named by stored data. - Encode and decode cached values through the registry and reject unknown or malformed tags.…

Public brief

Topic tags
Python
Storage & state

AnthropicCoding

Python codingWebAssembly + public tests

Reported interview periodJul 2025–May 2026

Implement a Quota-Aware Cloud File Store

Process a sequence of string commands against a flat cloud-storage namespace. Every command returns one result string.

Practice focusOperations - Add a file with a unique name and integer size; copy an existing file to a free name; query a file's size. - Find files matching both a prefix and suffix, sorted by size descending and then name ascending. - Add quota-limited users and add user-owned files only when capacity permits. - Reduce a user's capacity, evicting that user's largest files first and using name order to break ties until usage fits. - Compress an owned file by renaming it with a .COMPRESSED suffix and halving its even size.…

Public brief

Topic tags
Python
Storage & state
Networking

AnthropicCoding

Python codingWebAssembly + public tests

Reported interview periodMay 2026

Implement a DNS Resolver with Aliases and TTL

Build an in-memory resolver over A and CNAME records.

Practice focusRequirements - Normalize domain names case-insensitively and ignore a trailing dot. - An A record resolves directly to its address while live. - A CNAME follows its target recursively until a live A record is found. - Each record has type ( A or CNAME ) and value (address or target). Optional ttl is a duration; set at defaults to zero. A missing or null ttl means no expiration. - A record expires when now = set at + ttl . - Any expired or missing link makes resolution fail.…

Public brief

Topic tags
Python
Storage & state
Communication

AnthropicCoding

Python codingWebAssembly + public tests

Reported interview periodMay 2026

Implement a Task Manager with Expiration and Historical Views

Tasks are scoped by (user, task_id). Implement creation, mutation, TTL expiration, and snapshots.

Practice focusRequirements - A task key can be created only once, even if the task later completes or expires. - Only live incomplete tasks can be updated or completed. - TTL is anchored at creation; a task is absent at and after created at + ttl , and updates do not refresh it. - Current lists contain live incomplete titles ordered by task ID. - A historical list includes all events at or before the requested timestamp and applies expiration relative to that historical time. - Calls arrive in nondecreasing command time, though historical query times may be earlier.…

Public brief

Topic tags
Python
Data structures
Data / SQL

AnthropicCoding

Python codingWebAssembly + public tests

Reported interview periodOct 2025–May 2026

Design a Weighted, Checkpointable Data Batcher

You are training on several named datasets. A registry can open an iterator for a dataset at a supplied item offset. Design a batcher that mixes examples according to positive integer weights and can resume exa…

Practice focusThe supplied registry exposes get iterator(name, offset=0) , returning an iterator beginning at that dataset's zero-based item offset. It does not advance any other dataset. Implement the batcher, not the registry. Requirements - Every full batch contains exactly batch size examples while data remains available. - Allocate the integral share first, then distribute leftover slots using a deterministic largest-remainder carry across batches. - Break ties by the insertion order of weights and emit examples grouped in that same dataset order.…

Public brief

Topic tags
Python
Concurrency
ML / AI

AnthropicCoding

Python codingWebAssembly + public tests

Reported interview periodJan 2026–May 2026

Build a Workforce Time and Pay System

Implement employee time tracking, ranking, deferred promotions, and bonus-pay windows. Time is measured in integer ticks.

Practice focusRequirements - Each independent call sequence begins with a new Workforce. Add employees with sequential IDs e1 , e2 , and so on, even when names repeat. Mutation methods return None ; IDs are determined by insertion order rather than returned by add employee. - Inputs use integer, nonnegative timestamps and rates, with rate interpreted as pay per time tick. k is nonnegative; return at most k workers, including zero-work employees. Employee IDs are compared lexicographically for ties. - Count only completed half-open clock sessions [in, out) .…

Public brief

Topic tags
Python
Concurrency
Distributed systems
Storage & state
Data / SQL

AnthropicCodingHalf AI-generated

Talk-through codingNo local grader

Reported interview periodOct 2025–May 2026

Design Worker and Coordinator Protocols for Distributed Statistics

You control N workers and one coordinator. Worker i can read only shard i. Endpoints communicate by messages; there is no shared mutable dataset. Sending captures an independent snapshot of the payload; later s…

Practice focusThe task is either mode or median . For mode, return the globally most frequent integer with the smaller value winning ties. For median, return the exact middle value as a float, or the mean of the two middle values for even cardinality. The global input is non-empty; individual shards may be empty. Requirements - Define message shapes and an explicit completion condition. - Do not assume the coordinator can read worker data directly. - Avoid shipping complete raw shards in the scalable solution.…

Public brief

Topic tags
Python
ML / AI

AnthropicCodingHalf AI-generated

Talk-through codingNo local grader

Reported interview periodOct 2025–Apr 2026

Debug a GRPO Training Step

A small PyTorch implementation of Group Relative Policy Optimization runs without exceptions but learns poorly. Inspect and correct its sampling, advantage normalization, and clipped policy loss while preservin…

Practice focusRequired behavior - Convert logits to probabilities with softmax before sampling tokens. - For each prompt group, compute A i = (r i - mean(r)) / (std(r) + eps) using a positive epsilon so zero-variance groups remain finite. - Compute the per-token importance ratio as exp(current logprob - old logprob) . - Exclude masked tokens from both the loss sum and averaging denominator. - Compute the negative mean of the minimum between the unclipped and clipped ratio times advantage. - Return a finite zero loss if every token is masked.…

Public brief

Topic tags
Python
Algorithms
ML / AI
Product design

Coding exerciseCodingAI-generated

Practice formatRunnable coding45–70 min

Reported interview periodN/A

Build a token-budget batcher

Implement a small batching primitive, then adapt it to padded cost, bounded output, and production reasoning.

Practice focusPython, Greedy algorithms, Boundary cases, ML batching, Complexity through a runnable coding exercise.

Public brief

Topic tags
Python
Algorithms
Data structures
Storage & state
Networking

Coding exerciseCodingAI-generated

Practice formatRunnable coding45 min

Reported interview periodN/A

Sliding-window rate limiter

Build a limiter, then add quota reporting, retry timing, and independent keys.

Practice focusPython, Queues, State, Boundary cases, Complexity through a runnable coding exercise.

Public brief

Topic tags
Python
Algorithms
Data structures
Product design
Communication

Coding exerciseCodingAI-generated

Practice formatRunnable coding45 min

Reported interview periodN/A

Interval calendar

Reason about half-open intervals through conflicts, room counts, merging, and free slots.

Practice focusPython, Sorting, Intervals, Heaps, Edge cases through a runnable coding exercise.

Public brief

Topic tags
Python

Coding exerciseCodingAI-generated

Practice formatRunnable coding45 min

Reported interview periodN/A

Nested dictionary transforms

Flatten and reconstruct nested data, then support path access and lists.

Practice focusPython, Recursion, Data transformation, JSON-like data through a runnable coding exercise.

Public brief

Topic tags
Python
Storage & state

Coding exerciseCodingAI-generated

Practice formatRunnable coding45 min

Reported interview periodN/A

Command-log store

Evolve a tiny state machine through undo, compaction, and snapshot replay.

Practice focusPython, State machines, Undo logs, Compaction, Persistence through a runnable coding exercise.

Public brief

Topic tags
Python
Data structures
Reliability
Data / SQL

Coding exerciseCodingAI-generated

Practice formatRunnable coding50 min

Reported interview periodN/A

Dependency-ready scheduler

Turn a dependency graph into stable ready sets, execution layers, and failure impact.

Practice focusPython, Graphs, Stable ordering, Cycle detection, Failure analysis through a runnable coding exercise.

Public brief

Topic tags
Python
Data structures
Storage & state

Coding exerciseCodingAI-generated

Practice formatRunnable coding50 min

Reported interview periodN/A

Streaming metric window

Compute ordered rolling metrics, then partition state and expose freshness explicitly.

Practice focusPython, Queues, Streaming state, Boundaries, Observability through a runnable coding exercise.

Public brief

Topic tags
Python
Data / SQL

Coding exerciseCodingAI-generated

Practice formatRunnable coding50 min

Reported interview periodN/A

Evaluation slice aggregator

Aggregate pass rates, enforce minimum support, and compare evaluation runs without hiding weak slices.

Practice focusPython, Aggregation, Evaluation, Statistical hygiene, Determinism through a runnable coding exercise.

Public brief

Topic tags
Data structures
Concurrency
Storage & state
Reliability
ML / AI

System designSystem designAI-generated

Practice formatWritten response75–100 min

Reported interview periodN/A

Build a reliable job runner

Review staged prompts that begin with a small in-memory worker, then introduce retries, duplication, cancellation, and process restarts.

Practice focusState modeling, Idempotency, Retry policy, Failure recovery, Operational reasoning through a written response exercise.

Public brief

Topic tags
Communication

Hiring manager practiceHiring managerAI-generated

Practice formatWritten response30–45 min

Reported interview periodN/A

Defend your role fit

Connect motivation and scope to evidence from your work, then handle gaps, priorities, and expectations directly.

Practice focusMotivation, Role fit, Scope, Self-awareness, Questions through a written response exercise.

Public brief

Topic tags
Reliability
Communication

Project deep diveProject deep diveAI-generated

Practice formatWritten response60–90 min

Reported interview periodN/A

Prepare one project deep dive

Build a defensible walkthrough of a project from problem framing to architecture, experiments, failures, and outcomes.

Practice focusArchitecture, Experiment design, Debugging, Metrics, Trade-offs through a written response exercise.

Previous2 of 3Next

CONTENT BOUNDARY

Independent frontier AI interview practice. Includes adaptations of collected interview material and original exercises; not official company questions and not affiliated with the companies represented. Collected material does not predict future interview questions. Report a correction.

Loading the question catalog…

FREE PRACTICE

Public demos, always pinned.

Start with either demo. They remain here when you filter or sort.

Free account: sign in to practice the marked Free questions.

Newest published questions; deterministic, never randomized.

Demo 1Number search with delayed feedback
Demo 2Design real-time device monitoring and control

Question bank filters

Reset filters

Question groups

Filter question bank by interview groupAll 83 Coding 41 System design 10 Behavioral 15 Hiring manager 10 Project deep dive 7

Topics

Independent and not affiliated with the companies represented. Collected material does not predict future interview questions.

68 questions

Sort question bankSortFree first Newest Oldest AI ratio ↓AI ratio ↑

Question bank results

Every question has a public brief with the task, constraints, and follow-ups. Labels describe interactive practice access.

Public brief

Topic tags
Python

AnthropicCoding

Talk-through codingNo local grader

Reported interview periodJun 2026–Jul 2026

Repair a Looping Instruction Program

A small virtual machine executes a list of instructions over one integer accumulator. Blank lines and comment lines are ignored.

Public brief

Topic tags
Python

AnthropicCoding

Python codingWebAssembly + public tests

Reported interview periodJan 2025–Jul 2026

Build a Bank Ledger with Held Transfers and Account Merges

Implement an in-memory banking service whose operations arrive in nondecreasing timestamp order.

Public brief

Topic tags
Python
ML / AI

AnthropicCoding

Python codingWebAssembly + public tests

Reported interview periodSep 2025–Jun 2026

Implement a Longest-Match Tokenizer

Given an input string and a vocabulary, tokenize from left to right using longest-prefix matching.

Public brief

Topic tags
Python
Communication

AnthropicCoding

Python codingWebAssembly + public tests

Reported interview periodNov 2025–Jun 2026

Implement a Versioned Recipe Manager

Build an in-memory recipe service with unique names, search, users, and rollback.

Public brief

Topic tags
Python

AnthropicCoding

Python codingWebAssembly + public tests

Reported interview periodSep 2025–Jun 2026

Implement a Same-Host Web Crawler

Public brief

Topic tags
Python
Data structures
Reliability

AnthropicCodingHalf AI-generated

Talk-through codingNo local grader

Reported interview periodOct 2025–Jun 2026

Design a Type-Safe Durable LRU Cache

Extend a crash-recoverable LRU cache to support built-in containers and explicitly registered domain objects without using unsafe object serialization.

Public brief

Topic tags
Python
Storage & state

AnthropicCoding

Python codingWebAssembly + public tests

Reported interview periodJul 2025–May 2026

Implement a Quota-Aware Cloud File Store

Process a sequence of string commands against a flat cloud-storage namespace. Every command returns one result string.

Public brief

Topic tags
Python
Storage & state
Networking

AnthropicCoding

Python codingWebAssembly + public tests

Reported interview periodMay 2026

Implement a DNS Resolver with Aliases and TTL

Build an in-memory resolver over A and CNAME records.

Public brief

Topic tags
Python
Storage & state
Communication

AnthropicCoding

Python codingWebAssembly + public tests

Reported interview periodMay 2026

Implement a Task Manager with Expiration and Historical Views

Tasks are scoped by (user, task_id). Implement creation, mutation, TTL expiration, and snapshots.

Public brief

Topic tags
Python
Data structures
Data / SQL

AnthropicCoding

Python codingWebAssembly + public tests

Reported interview periodOct 2025–May 2026

Design a Weighted, Checkpointable Data Batcher

Public brief

Topic tags
Python
Concurrency
ML / AI

AnthropicCoding

Python codingWebAssembly + public tests

Reported interview periodJan 2026–May 2026

Build a Workforce Time and Pay System

Implement employee time tracking, ranking, deferred promotions, and bonus-pay windows. Time is measured in integer ticks.

Public brief

Topic tags
Python
Concurrency
Distributed systems
Storage & state
Data / SQL

AnthropicCodingHalf AI-generated

Talk-through codingNo local grader

Reported interview periodOct 2025–May 2026

Design Worker and Coordinator Protocols for Distributed Statistics

Public brief

Topic tags
Python
ML / AI

AnthropicCodingHalf AI-generated

Talk-through codingNo local grader

Reported interview periodOct 2025–Apr 2026

Debug a GRPO Training Step

Public brief

Topic tags
Python
Algorithms
ML / AI
Product design

Coding exerciseCodingAI-generated

Practice formatRunnable coding45–70 min

Reported interview periodN/A

Build a token-budget batcher

Implement a small batching primitive, then adapt it to padded cost, bounded output, and production reasoning.

Practice focusPython, Greedy algorithms, Boundary cases, ML batching, Complexity through a runnable coding exercise.

Public brief

Topic tags
Python
Algorithms
Data structures
Storage & state
Networking

Coding exerciseCodingAI-generated

Practice formatRunnable coding45 min

Reported interview periodN/A

Sliding-window rate limiter

Build a limiter, then add quota reporting, retry timing, and independent keys.

Practice focusPython, Queues, State, Boundary cases, Complexity through a runnable coding exercise.

Public brief

Topic tags
Python
Algorithms
Data structures
Product design
Communication

Coding exerciseCodingAI-generated

Practice formatRunnable coding45 min

Reported interview periodN/A

Interval calendar

Reason about half-open intervals through conflicts, room counts, merging, and free slots.

Practice focusPython, Sorting, Intervals, Heaps, Edge cases through a runnable coding exercise.

Public brief

Topic tags
Python

Coding exerciseCodingAI-generated

Practice formatRunnable coding45 min

Reported interview periodN/A

Nested dictionary transforms

Flatten and reconstruct nested data, then support path access and lists.

Practice focusPython, Recursion, Data transformation, JSON-like data through a runnable coding exercise.

Public brief

Topic tags
Python
Storage & state

Coding exerciseCodingAI-generated

Practice formatRunnable coding45 min

Reported interview periodN/A

Command-log store

Evolve a tiny state machine through undo, compaction, and snapshot replay.

Practice focusPython, State machines, Undo logs, Compaction, Persistence through a runnable coding exercise.

Public brief

Topic tags
Python
Data structures
Reliability
Data / SQL

Coding exerciseCodingAI-generated

Practice formatRunnable coding50 min

Reported interview periodN/A

Dependency-ready scheduler

Turn a dependency graph into stable ready sets, execution layers, and failure impact.

Practice focusPython, Graphs, Stable ordering, Cycle detection, Failure analysis through a runnable coding exercise.

Public brief

Topic tags
Python
Data structures
Storage & state

Coding exerciseCodingAI-generated

Practice formatRunnable coding50 min

Reported interview periodN/A

Streaming metric window

Compute ordered rolling metrics, then partition state and expose freshness explicitly.

Practice focusPython, Queues, Streaming state, Boundaries, Observability through a runnable coding exercise.

Public brief

Topic tags
Python
Data / SQL

Coding exerciseCodingAI-generated

Practice formatRunnable coding50 min

Reported interview periodN/A

Evaluation slice aggregator

Aggregate pass rates, enforce minimum support, and compare evaluation runs without hiding weak slices.

Practice focusPython, Aggregation, Evaluation, Statistical hygiene, Determinism through a runnable coding exercise.

Public brief

Topic tags
Data structures
Concurrency
Storage & state
Reliability
ML / AI

System designSystem designAI-generated

Practice formatWritten response75–100 min

Reported interview periodN/A

Build a reliable job runner

Review staged prompts that begin with a small in-memory worker, then introduce retries, duplication, cancellation, and process restarts.

Practice focusState modeling, Idempotency, Retry policy, Failure recovery, Operational reasoning through a written response exercise.

Public brief

Topic tags
Communication

Hiring manager practiceHiring managerAI-generated

Practice formatWritten response30–45 min

Reported interview periodN/A

Defend your role fit

Connect motivation and scope to evidence from your work, then handle gaps, priorities, and expectations directly.

Practice focusMotivation, Role fit, Scope, Self-awareness, Questions through a written response exercise.

Public brief

Topic tags
Reliability
Communication

Project deep diveProject deep diveAI-generated

Practice formatWritten response60–90 min

Reported interview periodN/A

Prepare one project deep dive

Build a defensible walkthrough of a project from problem framing to architecture, experiments, failures, and outcomes.

Practice focusArchitecture, Experiment design, Debugging, Metrics, Trade-offs through a written response exercise.

Previous2 of 3Next

CONTENT BOUNDARY