Summary
✨ AI‑Generated
Design, build, and ship production AI agents and the platform supporting them. Work across React interfaces, TypeScript and NestJS services, AWS infrastructure, and evaluation and feedback systems that measure agent performance. You will own systems used for critical day-to-day operational workflows.
Highlights
Own production AI systems across the full stack, from React interfaces and backend services to cloud infrastructure and agent evaluation. The role provides substantial ownership and focuses on measurable real-world operational outcomes rather than research or prompt engineering alone.
Description
We are looking for a Senior Full Stack AI Engineer.
You will design, build, and ship the agents described above and the platform they run on.
The work spans the full stack: React interfaces, NestJS services, AWS infrastructure, and the eval and feedback systems that determine whether an agent is actually performing.
Everything you build goes into production for customers moving real product on real deadlines.
This is a role for an engineer who wants ownership of systems that carry a customer's daily operations, not a research position or a prompt-engineering position.
Responsibilities
Production AI agents that run operational workflows end to end for food distributorsFull-stack features in TypeScript, NestJS, and React, shipped to production and maintained thereEval frameworks and feedback loops that measure and improve agent performance over timeLarge-scale order, catalog, and operational data at the application layerAWS infrastructure (Lambda, ECS, RDS, S3) managed with TerraformObservability as a first-class concern, with logging, tracing, and alerting built in from the start
Requirements
5 to 7 years of experience with Node.js, TypeScript, NestJS, and React in productionAt least one AI agent built, deployed, and running in production, beyond the prototype stage Applications deployed on AWS and serving real traffic (required)Hands-on experience with LLM and agent frameworks such as LangChain or LlamaIndexProduction use of observability tooling such as Datadog, OpenTelemetry, or CloudWatchExperience designing eval frameworks for AI systems and building self-learning or feedback-loop systemsDirect experience managing production incidents end to end, from detection through resolutionThe ability to clearly articulate and defend system design decisions you personally madeActive use of AI coding tools such as Cursor, Claude Code, or Copilot to increase output, grounded in a track record of writing production code before LLM-assisted development existed
