Burnt
Member of Technical Staff
San Francisco, CA · Staff+
Sponsorship not specifiedDetected 16 days ago
TypeScriptReactNode.jsFull-Stack DevelopmentAWSDatadogRESTLLMsAgentic AISupply ChainProcurementERPResearch
About the role
- This is a Member of Technical Staff position for a full stack engineer who lives at the intersection of product engineering and applied AI.
- You will be expected to architect systems, debug them when they break at 2am, and make them better the next morning.
Responsibilities
- Design, build, and ship full-stack features end to end, from data model to UI, that go live and stay live.
- Build production-grade AI agents and the eval frameworks that prove they work.
- Own production incidents end to end, from the page to the post-mortem to the fix that stops it recurring.
- Designed and implemented eval frameworks for AI systems.
Requirements
- Wrote production code before the LLM-assisted era, so you know what good code looks like without AI writing it for you.
Nice to have
- We don't believe ERPs will exist in the long run.
- They were built for a world where humans key in data and software stores it.
- That world is ending.
- A living, evolving brain that will run half of these businesses on autopilot.
- Not workflow tools.
- Not bolt-on automation.
- The things that live in inboxes, spreadsheets, phone calls, and people's heads.
- We're starting in food, a $1T+ industry that feeds the country and has been ignored by modern software.
Skills
- order management, procurement, reconciliation, vendor communication.
- The system doesn't just store data.
- It learns from it, adapts, and gets sharper the longer it runs.
- This isn't automation layered on legacy infrastructure.
- It's replacing the infrastructure entirely.
- This is not a research seat and it is not a prototype factory.
Benefits
- Stand up feedback loops and self-learning systems so the product gets sharper the more it runs.
- Built self-learning or feedback-loop systems.
This listing is sourced directly from Burnt's careers page and normalized into a canonical job model.