You'll work end-to-end: agent design, tool implementation, retrieval quality, integration into existing product UIs, cloud infrastructure, and evaluation/observability. The platform already ships to customers – you'll extend it, raise its quality bar, and help define where it goes next.
What you'll do
Design and evolve agents – build LLM agents with tool use, routing, and human-in-the-loop flows.
Implement tools and integrations – expose product capabilities to the agent, with multi-tenant context, via internal APIs and MCP servers.
Own retrieval quality – contribute to our RAG pipeline end-to-end: ingestion, embeddings, vector search, and reranking.
Define and evolve host integration contracts – collaborate with host application teams to integrate the assistant into product UIs built on different frontend stacks. You own the shared remote module and the integration API; host teams own their stacks.
Drive evaluation-led development – write evaluators (rule-based, LLM-as-judge, multi-turn), maintain CI eval gates, and use traces and feedback to debug production behavior.
Operate the platform – own deployments, observability, and the performance and cost of LLM-backed services.
Establish engineering practices** for AI-specific work: prompt versioning, eval coverage, testing, and code review.
5+ years of professional software engineering experience.
Strong TypeScript – the primary language across our backend, frontend, and agent code.
Production experience with LLM-based applications, including prompt engineering, agent/tool-calling design, and RAG.
Hands-on experience with an agent framework (e.g., LangGraph, LangChain).
Vector databases and semantic search with embedding-based retrieval.
Cloud experience on AWS – compute, storage, IAM, and managed LLM services (e.g., Bedrock or equivalent).
Solid web fundamentals – REST APIs, WebSockets, auth (token/OIDC), and modern React.
Docker and standard CI/CD practices.
