About the Role
This is the first full-time engineering hire outside the founding team at an early-stage AI/ML startup building tools that automatically detect failures in agent conversations and generate the patches to fix them. You'll own the entire loop — from data ingestion through patch generation and verification — and set the engineering culture everyone who comes after you will inherit.
What You'll Do
- Ship end-to-end: take problems from failure detection through ingest, patch generation, and verification into a product customers actively use.
- Own the trust surface — reproduction logic, guardrails, and checks that prevent bad PRs from reaching customer repositories.
- Move from customer conversation to shipped solution without waiting for formal specs or sign-off.
- Work directly with customers: read their traces, join their channels, and surface what broke before anyone else does.
- Make architectural calls that last — schema design, service boundaries, and speed-vs-correctness tradeoffs.
- Define engineering culture from scratch: testing standards, on-call practices, and ship criteria.
- Work across the full system — some weeks detection quality, some weeks the ingest pipeline, some weeks the review UI.
What We're Looking For
- 3+ years shipping production software with a demonstrated track record of working effectively outside your core specialty.
- Strong TypeScript proficiency across the full stack, from frontend through core services — it's the entire codebase.
- Real comfort with high-volume data: 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 optimizing systems for scale and cost awareness.
- Ability to take ambiguous customer problems and return well-considered solutions independently.
- Experience with observability, monitoring, and debugging production systems.
- Strong product sense — comfortable making architectural decisions with long-term system impact.
- Bonus: experience with PR review automation, code quality tooling, or early-stage founding team environments.
Compensation & Benefits
Salary range: $150,000 – $200,000 USD annually. Visa sponsorship is available.
Location
On-site in San Francisco, CA, United States.