JOBS / Mistral AI

Research Engineer, Inference Foundation

Munich; Warsaw; London

Role

The role involves developing and optimizing the core inference engine and orchestration for production LLM serving. Candidates must have experience with inference engines like vLLM and a solid grasp of inference internals such as KV-cache behavior and batching.

Location: Munich; Warsaw; London
Employment: unspecified
Work pattern: unspecified
Seniority: unspecified

vLLMKubernetesCUDAPythonPyTorch

APPLY ON THE EMPLOYER’S SITE ↗

Source and currency

This vacancy came from the organization’s official Ashby feed. Source update: 2026-10-06T13:03:50.922+00:00. Check the employer’s page for the complete description, current availability and application terms.

Mistral AI RESEARCH PROFILE ↗