AI Engineer

Full-time · Remote · ±4h GMT+5 overlap

Build AI features that survive contact with real users, not demos that impress in a meeting and break in production.

What you'll do

• —Design and ship AI features inside client products: retrieval, agents, tool calling, and evaluation
• —Own the unglamorous half: latency budgets, token cost, failure modes, and guardrails
• —Build the evaluation harness before the feature, so quality is measured rather than asserted
• —Tell clients honestly when AI is the wrong tool for their problem

What we're looking for

• —3+ years writing production software, with at least one shipped LLM-backed feature
• —Strong TypeScript or Python, and real fluency with at least one model provider's API
• —A working understanding of where models fail, not just where they impress
• —Comfortable reasoning about cost per request as a design constraint