Distributed Production Inference Engineer

Thinking Machines Lab Inc. is hiring a Software Engineer to design, build, and scale distributed production inference systems for Inkling, Inkling-Small, and Tinker.

You will own the end-to-end serving stack, from request routing to multi-node coordination and GPU utilization at scale. The role emphasizes production-first systems work, latency optimization, and deep observability, collaborating with research and infrastructure teams to translate evolving model architectures into reliable