Research Engineer, Inference Foundation

Mistral AI; Greater London; Hybrid; GBP 120,000 - 180,000; Full time

Benefits offered by this job

Healthcare coverage

Relocation support

Wellness programs

Job summary

Mistral AI is seeking a senior engineer to own and optimize the inference stack, engine orchestration, and scalable serving for frontier AI models. You will work on production-grade ML/LLM services, capacity sizing, and training-serving pipelines to keep models responsive and cost-efficient.

The role emphasizes building high-performance serving systems, with hands-on experience in vLLM, SGLang, or TensorRT-LLM, and deep CUDA/NCCL knowledge. Hybrid work in London area is supported.

Qualifications

• Experience building and running ML/LLM services at scale with latency/availability targets.
• Hands-on experience with inference engines such as vLLM, SGLang, TensorRT-LLM or equivalents.
• Solid grasp of inference internals: prefill vs decode, KV-cache, batching, scheduling, parallelism strategies.
• Familiar with distributed and disaggregated serving architectures.

Responsibilities

• Develop and fix the core of the inference stack — engine and orchestrator — for max performance at scale.
• Own the release process for the serving stack with automated performance gates and progressive rollout.
• Drive improvements upstream when open-source engine is appropriate.
• Optimize serving efficiency across the fleet and topology for best throughput and latency.
• Build serving infra powering RL and post-training workloads.

Skills

ML at scale

Inference engines

Python

PyTorch

Kubernetes

CUDA/NCCL

GPU hardware

Networking

Distributed systems

Tools

vLLM

SGLang

TensorRT-LLM

Job description

About Mistral

Mistral provides full-stack AI solutions: from frontier models to developer tools, applications, and compute. We partner with enterprises tackling the hardest problems across high-stakes industries like finance, manufacturing, defense, healthcare, and the public sector, co-creating customized AI systems that they can run on their terms.

We are a dynamic, collaborative team passionate about AI and its potential to transform society. Our diverse workforce thrives in competitive environments and is committed to driving innovation. Our teams are distributed between Europe, North America, Asia and the Middle East. We are creative, low-ego and team-spirited.

The Role

The Inference Foundation team owns the core of Mistral's inference stack: the inference engine and its orchestration, from the feature set and configuration that serve our models in production to the release machinery that keeps the stack current and production-grade.

This is a hybrid position spanning production LLM serving, engine and platform development, and capacity engineering. You will work on three intertwined problems:

1. Optimize the inference stack at scale — feature development and fixes in the engine and orchestrator, squeezing more throughput and lower latency out of every GPU under strict quality-of-service targets.

2. Make capacity elastic — scaling up and down should be cheap and fast, not a performance cliff.

3. Power the training of our frontier models — high-performance serving that keeps RL and post-training loops running at full speed.

What You Will Do

Inference engine & orchestration

• Develop and fix the core of the inference stack — engine and orchestrator — including feature selection, configuration, and tuning for maximum performance at scale

• Own the release process for the serving stack: validated, regression-free releases through automated performance gates and progressive rollout

• Drive improvements and fixes upstream when the open-source engine is the right place for them

Performance & capacity at scale

• Optimize serving efficiency across the fleet — driving down pod startup time, tackling cold-cache regressions on scale-up, smarter caching and offloading

• Optimize and maintain the optimal serving topology — overlap communication and transfers with computation, ensure optimal placement, connectivity, and routing

Serving for frontier training

• Build the serving infrastructure that powers RL and post-training for our frontier models

• Optimize inference performance across the full spectrum of our workloads

What We're Looking For

• 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

It Would Be Great If You Have

• Demonstrated vLLM/sglang know-how — upstream contributions, or a track record of running in demanding production environments

• Hardware-aware optimization for various model architectures

• Experience serving MoE models at scale (expert parallelism, expert placement/load balancing)

• CUDA/Triton kernel development; Nsight Systems/Compute profiling

• Rust and/or C++ in production systems

What We Offer

We offer a comprehensive benefits package designed to support your well-being, growth, and work-life balance. Benefits vary by country and may include healthcare coverage, parental leave, retirement plans, relocation support, wellness programs, meal and transportation allowances, and other location-specific perks.

For the most up-to-date details on benefits available in your location, please refer to our Benefits page.

Privacy Policy

Your privacy matters to us. You can learn more about how we handle your personal data in our Applicant Privacy Policy.