Staff ML engineer optimizing LLM inference for speed, cost, and reliability.
Lead infrastructure-level optimization work for production language model serving, including quantization, caching strategies, and speculative decoding. You'll partner with kernel engineers and infrastructure teams to reduce latency and cost per token across diverse model families. This role requires hands-on expertise deploying modern inference engines and deep knowledge of transformer bottlenecks, suited for someone with 5+ years optimizing high-throughput ML systems.
Membership is €29/month, cancel anytime: every rate, every original listing link, and a daily alert for roles matching your filters.
Found at a specialist agency · listed 22 October 2026 · InsideJobs links you to the original posting.