Opis tej firmy nie jest jeszcze dostępny w tym języku.
Research Engineer, Inference Foundation
Mistral AI recrute un Research Engineer au sein de l’équipe Inference Foundation pour développer et optimiser l’infrastructure d’inférence LLM à grande échelle. Le poste couvre l’orchestration du moteur d’inférence, la capacité élastique, le serving haute performance et l’infrastructure des entraînements de modèles avancés. Une expérience des services ML/LLM, de Kubernetes, des GPU et d’outils comme vLLM, SGLang ou TensorRT-LLM est recherchée.
3× plus de chances d’entretien avec un cold email
Zobacz oryginalną ofertęInformacje o Mistral AI
- Branża
- Oprogramowanie i internet
- Model
- B2B
- Typ firmy
- Finansowana przez fundusz venture capital
- Etap rozwoju
- Jednorożec
- Siedziba
- Paris
- Oficjalna domena
- mistral.ai
- Rok założenia
- 2023 · 3 lata
- Opublikowana wycena
- 24 Md$Źródło ↗
- Opublikowana łączna kwota finansowania
- 7,5 Md$Źródło ↗
- Ostatnia runda finansowania
- Series D · 2026-09-08
- Ogłoszona kwota
- 3 500 000 000 $
- Aktualne oferty
- 194
Wymienieni inwestorzy
Szczegóły oferty
Pełny opis opublikowany przez Mistral AI.
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.
Wymagania
- Experience building and running ML/LLM services at scale
- Familiarity with distributed and disaggregated serving architectures
- GPU and networking fundamentals
Wymienione benefity
- healthcare coverage
- parental leave
- retirement plans
- relocation support
- wellness programs
- meal allowances
- transportation allowances
Aplikuj na tę ofertę
Jak aplikować?
Oferta jest opublikowana na stronie Mistral AI. Otwórz oryginalną ofertę ↗ aby wysłać aplikację. Screeningpass nie wypełnia formularza za Ciebie.
Do kogo w Mistral AI napisać w sprawie tego stanowiska?
Rozpocznij wyszukiwanie kontaktu na tej stronie. Screeningpass zaproponuje Ci maksymalnie trzy osoby związane ze stanowiskiem. Wybierz osobę, do której chcesz napisać, a Screeningpass poszuka jej służbowego adresu e-mail i przygotuje wiadomość. Sprawdź ją i wyślij samodzielnie przez Gmail. Adres e-mail nie zawsze jest dostępny i nigdy nie ma gwarancji odpowiedzi.
Ile kosztuje wyszukanie kontaktu?
Jedno wyszukiwanie kosztuje 1 kredyt. Jeśli wyszukiwanie się nie powiedzie, kredyt wróci na Twoje konto. Za rejestrację otrzymasz 3 kredyty, czyli 3 wyszukiwania.
Do czego służy Screeningpass?
Screeningpass zbiera publikowane przez firmy oferty staży, kształcenia dualnego i pracy. Dla danej oferty Screeningpass znajduje osobę do kontaktu w firmie, szuka jej służbowego adresu e-mail i przygotowuje wiadomość na podstawie Twojego CV. Zobacz szczegółowo, jak to działa.