Lemma

Production Monitoring for AI agents

Founding Engineer

$150K - $200K1.00% - 2.00%San Francisco, CA, US
Job type
Full-time
Role
Engineering, Full stack
Experience
Any (new grads ok)
Visa
US citizen/visa only
Connect directly with founders of the best YC-funded startups.
Apply to role ›
Jerry Zhang
Jerry Zhang
CEO

About the role

Lemma reads all of your agent conversations, finds the failures nobody knew to look for, and opens the PR that fixes them.

Why this role exists

You'd be the first engineer here who isn't a founder or a contractor.

That means there's no engineering culture waiting for you to join it. The testing standards, the on-call story, how we decide what ships on a Friday, all of that is currently whatever the two of us happened to do last month. You'd be setting it, and you'd be living with it longer than we will.

There's also no work stream attached to this job. You go where the gap is. Some weeks that's detection quality, some weeks it's the ingest pipeline choking on a customer whose instrumentation is a mess, some weeks it's the review UI that decides whether someone trusts our PR enough to merge it. We hire this role because the constraint on a team this size is almost never a specialist.

What you'll do

  • Ship across the whole loop: ingest, detection, patch generation, verification, the product people actually look at
  • Own the trust surface. Reproduction, guardrails, and the checks that keep a bad PR from ever reaching a customer's repo
  • Take a problem from a customer conversation to something shipped, without waiting for a spec
  • Talk to customers directly. You'll be in their Slack, reading their traces, hearing what broke before we do
  • Make calls that outlive you. Schema decisions, service boundaries, what we're willing to be slow about

What we're looking for

  • 3+ years shipping production software, and a track record of shipping well outside whatever you'd call your specialty
  • Strong TypeScript. It's the whole codebase, frontend through the core service
  • Real comfort with data at volume. You've thought about cost per event, not just correctness
  • Strong product sense. You can take a rough problem and return something well considered without a Figma file waiting for you
  • You've built with agents and have opinions about why they fail
  • Bonus: you were the customer once. You ran agents in production and got burned

We move fast on hiring. Target is an offer within two weeks of first contact.

Onsite in San Francisco. We sponsor visas.

About the interview

We keep this short on purpose. Target is an offer within two weeks of first contact.

Intro call with a founder (30 minutes). What we're building, what you've built, whether the shape of the role actually fits what you want next.

Take-home project and deep dive. We give you a real problem from Lemma. You work on it on your own time, then we walk through it together. The conversation matters more to us than the artifact.

Paid work trial (2 days, onsite in-person). Real problem, real codebase, sitting with the team. You find out what working here actually feels like before you commit, which tells you more than anything we could say about it.

May ask for additional references.

About Lemma

Lemma is a YC F25 company building production monitoring for AI agents. We help companies automatically improve their AI agents from production data by catching the silent failures your observability tools miss and building self-healing loops.

We're backed by Y Combinator, Matrix, Liquid 2 and operators from OpenAI, xAI, and Doordash. We look for people who act like founders - driven by the mission, biased toward action, and committed to craft.

Lemma
Founded:2025
Batch:F25
Team Size:2
Status:
Active
Location:San Francisco
Founders
Cole Gawin
Cole Gawin
CTO
Jerry Zhang
Jerry Zhang
CEO