Research Engineer, Inference Foundation

Mistral
Paris +2 more
Hybrid

Who this role is best for

Candidates with experience in distributed AI infrastructure and inference optimization will find this role in production LLM serving and capacity engineering at Mistral.

Best fit for

  • Candidates with production experience in inference engines and distributed serving architectures
    — “Experience building and running ML/LLM services at scale, with clear latency and availability targets”
  • Individuals skilled in optimizing GPU performance and managing large-scale AI workloads
    — “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”
  • Professionals with a background in high-performance computing and systems-level debugging
    — “Comfortable debugging across the full stack — CUDA/NCCL, kernels, containers, networking, storage”

Things to consider

  • The role demands a strong grasp of GPU and networking fundamentals, which may require specialized training or experience.
    — “GPU and networking fundamentals: CUDA runtime, NCCL, InfiniBand/RDMA”
  • Candidates must be prepared to work in a globally distributed team, with potential for collaboration across multiple time zones.
    — “Our teams are distributed between Europe, North America, Asia and the Middle East”

How to stand out

  • Highlight your experience with optimizing inference engines like vLLM or TensorRT-LLM in production environments.
    — “Hands-on experience with inference engines such as vLLM, SGLang, TensorTrt-LLM, or others”
  • Demonstrate your familiarity with Kubernetes for managing large-scale AI infrastructure.
    — “Kubernetes for running infrastructure at scale”
  • Showcase your track record with distributed and disaggregated serving architectures in your resume and interviews.
    — “Familiarity with distributed and disaggregated serving architectures”
  • Include projects or contributions related to MoE models or hardware-aware optimizations if applicable.
    — “Experience serving MoE models at scale (expert parallelism, expert placement/load balancing)”
Pace · SteadyCollaboration · HighAutonomy · MediumDecision Impact · Team

Derived from job-description analysis by Serendipath's career intelligence engine.

What success looks like

  • Optimize the inference stack at scale
  • Make capacity elastic
  • Power the training of frontier models
  • Build the serving infrastructure for RL and post-training
Typical background
Experience building and running ML/LLM services at scaleHands-on experience with inference enginesSolid grasp of inference internals

Skills & requirements

Required

LLM ServingInference EnginesVllmSglangTensorrt-llmDistributed And Disaggregated Serving ArchitecturesCuda/ncclKubernetesGPU And Networking FundamentalsPythonPyTorch

Preferred

Vllm/sglang Know-howUpstream ContributionsRunning In Demanding Production Environments

Stack & domain

Ml/llm ServicesInference EnginesVllmSglangTensorrt-llmPre-fill Vs. DecodeKv-cache BehaviorBatchingSpeculative DecodingParallelism StrategiesDistributed And Disaggregated Serving ArchitecturesCuda/ncclKernelsContainersNetworkingStoragePythonPyTorchKubernetesGPU And Networking FundamentalsDebuggingTeamworkInnovationAI SolutionsEnterprise AIFinanceManufacturingDefenseHealthcarePublic SectorInference StackLLM ServingEngine And Platform DevelopmentCapacity Engineering

About the role

Original posting from Mistral via Ashby

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:

  • 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.
  • Make capacity elastic — scaling up and down should be cheap and fast, not a performance cliff.
  • 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 https://app.notion.com/p/mistralai/Benefits-at-Mistral-36e6ba59a7fe836b93dd01737fcc27ef?source=copy_link.

PRIVACY POLICY

Your privacy matters to us. You can learn more about how we handle your personal data in our Applicant Privacy Policy https://legal.mistral.ai/terms/applicant-privacy-policy.

Source: Mistral careers (Ashby)

Similar roles

More roles at Mistral