Description
You will build and ship production-grade AI systems, owning the full path from development to deployment.
This role is remote.
Responsibilities
- Design and implement backend services using Python and/or TypeScript with robust API design.
- Integrate LLM APIs (OpenAI, Anthropic) into production products, managing function calling, structured outputs, and latency.
- Develop agentic systems that manage state, invoke tools, and handle failure recovery using LangGraph or LangChain.
- Build evaluation infrastructure to measure system performance and reliability before release.
- Collaborate with product management to define feature requirements and ensure customer value.
Required Skills
- 5+ years of backend engineering experience with shipped software.
- Proficiency in Python and/or TypeScript.
- Experience with API design and production databases.
- Hands-on experience with LLM API integration beyond demo projects.
- Practical knowledge of agentic frameworks (LangGraph, LangChain, LlamaIndex).
- Ability to reason through state management and tool invocation in AI systems.
- Experience shipping in teams of fewer than five people.
Preferred Skills
- Hands-on RAG experience with chunking strategies and vector store tradeoffs.
- Experience with Langfuse, LangSmith, or Arize Phoenix for observability.
- Cloud deployment experience (AWS, GCP, Azure), Docker, and CI/CD.