AI Engineer

Role overview A hands-on engineering position focused on the LLM-powered systems that power client-facing software. The work centers on building and shipping production-grade features such as conversational agents, retrieval-augmented generation (RAG) pipelines, and tool-using assistants, while making sure they remain reliable and well-instrumented once they reach real users.

Responsibilities - Design, build, and ship LLM-backed product features including chat interfaces, autonomous agents, retrieval flows, and tool integrations. - Add evaluation suites, guardrails, and safety checks so that model behavior remains consistent and trustworthy in production. - Track the fast-moving landscape of models and frameworks, evaluate new options, and recommend what is genuinely worth adopting. - Partner with other engineers to help them apply AI tooling effectively in their own workflows.

Requirements - Track record of shipping LLM-powered features to real users, beyond prototypes and demos. - Strong backend fundamentals, including API design, data modeling, and operating services in production. - Working knowledge of retrieval techniques, prompt design, and the principles of evaluating model output critically. - Model-agnostic approach: ability to choose the right model or framework for a given problem rather than defaulting to a favorite.

Nice to have - Hands-on experience with frameworks such as the Vercel AI SDK, LangChain, or comparable alternatives. - Familiarity with vector databases and embedding-based search.