Research Engineer, Inference Foundation

Highlights

• Own the core inference engine and orchestration powering Mistral models.
• Make GPU capacity elastic with fast scale-up and smarter caching.
• Build high-performance serving that powers RL and frontier model training.

What they offer

• healthcare coverage
• parental leave
• retirement plans
• relocation support
• wellness programs
• meal and transportation allowances

Ideal candidate

A systems-minded engineer who thrives on production-scale performance puzzles and low-ego collaboration. You care about squeezing efficiency from GPUs while keeping frontier training and serving reliable.

Requirements

• Experience building and running ML/LLM services at scale, with clear latency and availability targets
• Hands-on experience with inference engines such as vLLM, SGLang, TensorRT-LLM, or others
• A solid grasp of inference internals: prefill vs. decode, KV-cache behavior, batching, scheduling, speculative decoding, parallelism strategies
• Familiarity with distributed and disaggregated serving architectures
• Comfortable debugging across the full stack — CUDA/NCCL, kernels, containers, networking, storage
• Python for systems tooling and backend services; PyTorch
• Kubernetes for running infrastructure at scale
• GPU and networking fundamentals: CUDA runtime, NCCL, InfiniBand/RDMA