La descripción de esta empresa todavía no está disponible en este idioma.
Research Engineer, Inference Foundation
Mistral AI incorpora un Research Engineer al equipo Inference Foundation para desarrollar y optimizar la infraestructura de inferencia LLM a gran escala. El puesto abarca la orquestación del motor de inferencia, la capacidad elástica, el servicio de inferencia de alto rendimiento y la infraestructura de entrenamiento de modelos avanzados. Se busca experiencia en servicios ML/LLM, Kubernetes, GPU y herramientas como vLLM, SGLang o TensorRT-LLM.
3× plus de chances d’entretien avec un cold email
Ver la oferta originalDatos sobre Mistral AI
- Sector
- Software e Internet
- Modelo
- B2B
- Tipo de empresa
- Financiada con capital riesgo
- Fase
- Unicornio
- Sede
- Paris
- Dominio oficial
- mistral.ai
- Fundación
- 2023 · 3 años
- Valoración publicada
- 24 Md$Fuente ↗
- Financiación total publicada
- 7,5 Md$Fuente ↗
- Última ronda
- Series D · 2026-09-08
- Importe anunciado
- 3 500 000 000 $
- Ofertas abiertas
- 194
Inversores mencionados
Detalles de la oferta
La descripción completa publicada por 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.
Requisitos
- Experiencia en la creación y operación de servicios ML/LLM a gran escala
- Familiaridad con arquitecturas de servicio distribuidas y desagregadas
- Fundamentos de GPU y redes
Ventajas mencionadas
- cobertura sanitaria
- permiso parental
- planes de jubilación
- ayuda para el traslado
- programas de bienestar
- ayudas para comidas
- ayudas para el transporte
Inscribirme en esta oferta
¿Cómo inscribirme?
La oferta está publicada en el sitio de Mistral AI. Abre la oferta original ↗ para enviar tu candidatura. Screeningpass no rellena formularios por ti.
¿A quién escribir en Mistral AI para este puesto?
Inicia una búsqueda de contacto desde esta página. Screeningpass te propone hasta tres personas vinculadas al puesto. Tú eliges a quién escribir y Screeningpass busca su correo profesional y prepara un mensaje. Lo revisas y lo envías tú con Gmail. No siempre hay una dirección de correo disponible y nunca se garantiza una respuesta.
¿Cuánto cuesta buscar un contacto?
Una búsqueda cuesta 1 crédito. Se te devuelve si la búsqueda falla. Al registrarte recibes 3 créditos, para hacer 3 búsquedas.
¿Para qué sirve Screeningpass?
Screeningpass reúne ofertas de prácticas, formación dual y empleo publicadas por las empresas. Para una oferta, Screeningpass encuentra una persona con la que contactar en la empresa, busca su correo profesional y prepara un mensaje a partir de tu CV. Ver el funcionamiento en detalle.