We're looking for AI engineers who can build, deploy, and debug AI agents in production.
???? ??'?? ??????? ???:
- Experience building agents from scratch, not just wrapping LLM APIs.
- Strong understanding of agent frameworks, orchestration, tool calling, context management, and custom harnesses.
- Ability to debug agents at scale, analyze execution traces, identify failure patterns, and improve reliability.
- Experience with agent evaluations, observability, and performance optimization.
- Strong Python and software engineering fundamentals.
- Ability to work directly with customers, navigate ambiguous problems, and ship end-to-end solutions.
?????: Experience with Claude Code, Codex, OpenHands, LangGraph, or custom agent infrastructure.
We're not looking for someone who can just make an agent work once. We're looking for engineers who understand why agents fail and know how to make them work reliably.
??????????? DM me with your resume, GitHub, or something compelling you've built.