Global AI MapJOBS / Mistral AI
Research Engineer, Latency & Throughput
Paris; London
Role
The role involves researching and prototyping techniques to reduce latency and increase throughput in LLM inference, such as speculative decoding and quantization. Candidates must have a strong ML background, hands-on Python and PyTorch experience, and a track record of conducting experiments.
Location: Paris; London
Employment: unspecified
Work pattern: hybrid
Seniority: unspecified
APPLY ON THE EMPLOYER’S SITE ↗
Source and currency
This vacancy came from the organization’s official Ashby feed. Source update: 2026-10-20T11:22:45.254+00:00. Check the employer’s page for the complete description, current availability and application terms.