Research Engineer, Latency & Throughput

Join Mistral, a leading AI solutions provider, as a Research Engineer on the Latency & Throughput team. In this role, you will research and prototype techniques to reduce latency and increase throughput in LLM inference. You will work closely with inference engineers and research scientists, generating new ideas and implementing proof-of-concepts. The position is based in Paris or London, with remote options available for senior profiles.

Responsibilities

• Research and prototype inference techniques to reduce latency and increase throughput in LLM inference.
• Design and run experiments to validate or refute ideas, iterating quickly on small-scale setups before proposing production integration.
• Collaborate with the Inference Foundation team to integrate validated techniques into the vLLM-based serving stack.