Intro
We're looking for a software developer who has actually shipped products that put LLMs and agentic workflows in the hands of real users. If you've wrestled with prompt reliability at scale, designed agent loops that don't fall apart in production, and care deeply about building things people love to use, we want to talk.
What you'll do
You'll own features end-to-end across the stack: React/TypeScript on the frontend, Node.js services on the backend, all running on AWS. You'll design and build agentic systems, work on the LLM integration layer, and make critical decisions about how AI-native product experiences are architected. Ship fast, iterate based on what you learn, and raise the bar for the whole team.
You will write very little code. We are heavy users of AI coding tools (Claude Code, Codex, whatever makes you faster) and expects you to be fluent with these tools or eager to become so. Strong views on how AI changes the way teams build software are a plus.
What we're looking for
Strong production experience with React, TypeScript, Node.js, and AWS
Hands-on experience shipping LLM-powered features to real users: prompt engineering, retrieval-augmented generation, tool use, agent orchestration, eval frameworks, or similar
A track record of building and delivering products, seeing features through from idea to production to iteration
Comfort working with ambiguity
Strong opinions on software quality, testing, and system design, held loosely enough to move fast
Nice to have
Experience with agent frameworks (LangChain, AI SDK, LangGraph, Mastra, custom orchestration)
Background in developer tooling or platform work
Familiarity with observability for LLM systems (tracing, cost tracking, latency optimization)
Prior startup or high-growth environment experience
Contributions to open-source AI/ML projects
Benefits
