Founding Engineer
About the Role
This is the first full-time engineering hire outside the founding team at an early-stage AI/ML startup building automated agent failure detection and patch generation tooling. You will own the entire loop, from conversation ingestion and failure detection through patch generation and verification, and you will set the engineering standards everyone who follows you will inherit.
What You'll Do
Ship end-to-end: take problems from detection through ingest, patch generation, and verification into the product customers use.
Own the trust surface, including the reproduction logic, guardrails, and checks that keep bad PRs from reaching customer repositories.
Move from customer conversation to shipped solution independently, without waiting for specs or sign-off.
Talk to customers directly: read their traces, join their Slack channels, and surface what broke before the rest of the team does.
Make architectural calls that outlast you: schema design, service boundaries, and tradeoffs between speed and correctness.
Define engineering culture from scratch, including testing standards, on-call practices, and release criteria.
Work across the full system: detection quality, ingest pipelines, and the review UI that determines whether a customer trusts your PR.
What We're Looking For
3 or more years shipping production software with a strong track record of working well outside your core specialty.
Strong TypeScript proficiency across the full stack, frontend through core services (the entire codebase is TypeScript).
Real comfort with data at volume: you think in cost-per-event, not just correctness.
Experience building and operating AI agents in production, with clear opinions on how and why they fail.
Experience designing data pipelines and systems that handle high-volume event data with cost awareness.
Experience making architectural decisions (schema design, service boundaries) that shape long-term system design.
Strong product sense: you can take rough, open-ended problems and return well-considered solutions without designs handed to you.
Bonus: experience with PR review automation, code quality tooling, or observability and monitoring in production systems.
Compensation & Benefits
Base salary between $150,000 and $200,000 USD annually. Visa sponsorship is available.
Location
On-site in San Francisco, California.