baseten

Small

Baseten is a machine learning infrastructure company that provides a platform for deploying, serving, and scaling AI and ML models in production. It is known for enabling developers and businesses to run inference workloads efficiently without managing complex underlying infrastructure.

3 interview notes · updated Jul 2026

baseten·Software Engineer·Onsite - System Design / Architecture

Jun 2026

System design round at Baseten focused entirely on building a CI/CD platform from scratch. Pretty intense scope for a single session, they wanted depth on basically every layer of the stack.

Design a CI/CD platform for engineering teams. Walk through pipeline definition, source control integration, build agents, artifact storage, deployment strategies, secret management, observability, and access control.
How would you handle queueing fairness across different teams sharing the same build infrastructure?
How do you guarantee tenant isolation in a shared CI/CD environment?
What does a reproducible build actually require, and where does it typically break down?

“This was a lot.”

View Post

baseten·Software Engineer·Technical Phone Screen

May 2026

Baseten coding round where they gave you a working sequential file downloader and asked you to make it parallel. More involved than it sounds once you get into the error handling and assembly order stuff.

You're given a sequential file downloader that fetches chunks one at a time. Refactor it to download chunks in parallel with bounded concurrency, correct in-order assembly, per-chunk retries, fail-fast on unrecoverable errors, and graceful cancellation.
How do chunk size and concurrency level interact to affect download throughput, and what are the tradeoffs when tuning them?

“This is a meaty one.”

View Post

baseten·Software Engineer·Onsite - System Design / Architecture

Apr 2026

Follow-up system design round at Baseten focused on the integrity verification side of a parallel S3 chunk downloader. Pretty deep dive, more about correctness guarantees and testability than the happy path.

After building a parallel chunk downloader for S3, how do you verify that every chunk arrived correctly and the reassembled file actually matches what the server has?
If a chunk checksum or the final file hash doesn't match the expected value, do you retry that chunk, abort the whole download, or something else? What's your decision logic?
How would you unit and integration test this downloader, including fault injection on individual chunks?

“This is where I spent most of the time.”

View Post