---
title: 'Research Engineer, Inference Foundation at Mistral'
canonical: 'https://feeny.ai/job/research-engineer-inference-foundation-mistral-munich-m3qct64grrv2'
type: 'job'
last_seen: '2026-11-08'
---

# Research Engineer, Inference Foundation at Mistral

- **Company:** [Mistral](https://feeny.ai/companies/mistral)
- **Location:** Munich, Germany
- **Employment:** full-time
- **Work type:** hybrid
- **Posted:** 2026-10-06
- **Last confirmed live:** 2026-11-08
- **Apply:** https://jobs.ashbyhq.com/mistral.ai/162e8d27-8a88-403e-9f35-2bf541b387d7

## 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:

- 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).

## About Mistral

## Company Overview
- **One-liner**: Mistral is a French AI company building open, frontier-grade large language models, developer platforms, and applied AI solutions for enterprises and governments.
- **Entity Type**: Private (Series C)
- **Headquarters**: Paris, France (15 rue des Halles)
- **Founded**: April 2023
- **Founders**: Arthur Mensch (CEO), Guillaume Lample (Chief Science Officer), Timothée Lacroix (CTO)

## Core Business
- **Primary industry/industries**: Artificial Intelligence, Large Language Models, Enterprise AI Software
- **Target customers**: B2B, Enterprise, Government, and Developers (B2D)
- **Mission or purpose statement**: "To make frontier AI open to all, and together solve the world's hardest problems."

## Products & Services
- **Mistral Large**: Frontier-grade large language model for complex reasoning and enterprise tasks.
- **Mistral Small 3**: Efficient, lightweight model for cost-sensitive deployments.
- **Mistral Code / Vibe**: AI agent for long-horizon, autonomous software development and task completion.
- **Le Chat**: Consumer-facing AI assistant and chatbot.
- **Mistral OCR 4**: State-of-the-art document intelligence model for extracting and understanding text from images and PDFs.
- **Mistral Forge**: Custom model development service for training, aligning, and evaluating proprietary AI models on private data.
- **Mistral Studio**: Platform for building, testing, and running AI agents and applications with full control.
- **Mistral Compute**: Infrastructure and orchestration platform for frontier-scale training and inference (edge to cloud).
- **Mistral Search Toolkit**: Tools for integrating search and retrieval into AI applications.
- **Voxtral**: Voice AI model for speech-based interactions.

## Market Standing
- **Valuation/Market Cap**: $4.016 billion (latest reported valuation, per CB Insights; date not specified but likely post-Series C)
- **Key Metric**: Total funding raised across Seed, Series A, Series B, and Series C rounds (specific amounts not disclosed in search results).
- **Notable Investors/Partners**: Not explicitly named in search results, but the company partners with organizations in finance, manufacturing, defense, energy, and the public sector.
- **Growth Signals**: 
  - Rapid scaling: 900+ employees across 30+ nationalities as of mid-2026.
  - 50% of leadership roles held by women.
  - Key product launches on a near-monthly cadence (e.g., Mistral OCR, Forge, Vibe, Compute, Search Toolkit, Voxtral).
  - Strong presence in high-stakes, regulated industries (defense, energy, public sector).

## Competitive Advantages
- **Open-source DNA**: Commitment to openness, transparency, and cost efficiency differentiates Mistral from closed, Big Tech AI labs.
- **Full-stack ownership**: Controls the entire stack from frontier models to developer tools, applications, and compute infrastructure, enabling deep customization and reliability.
- **European leadership**: Positioned as a sovereign, European AI champion, appealing to governments and enterprises seeking data control and regulatory compliance.
- **Speed and rigor**: Culture of rapid experimentation, iteration, and data-driven decision-making.

## Strategic Focus
- **Enterprise and government partnerships**: Co-creating tailored AI systems for mission-critical use cases in finance, manufacturing, defense, energy, and public sector.
- **Open platform ecosystem**: Expanding Mistral Studio and Forge to enable customers to build custom models and agents on their own data.
- **Infrastructure as a product**: Commercializing Mistral Compute to become a platform for others to train and run AI workloads.
- **Continuous model innovation**: Releasing new frontier models and capabilities (OCR, voice, code agents) at a rapid pace.

## Why Work Here
- **Culture**: Flat structure, high ownership, low ego, and a "builders, not order takers" mentality. The company values audacity, speed, rigor, and customer centricity.
- **Remote/Hybrid/Office**: Based in Paris (15 rue des Halles); relocation support and visa sponsorship offered. Specific remote/hybrid policy not detailed, but global team suggests flexibility.
- **Notable perks and benefits** (from careers page):
  - 20 weeks paid parental leave for all birthing parents.
  - 100% employer-sponsored medical, dental, and vision coverage for employees and dependents.
  - 6% 401k match (US) / 5% pension contribution (UK).
  - Childcare support (reserved daycare seats or financial assistance).
  - Meal allowances and transportation support.
  - Fitness and wellness subsidies.
  - Relocation and settling-in services.
  - Financial and career planning support.
- **Team composition**: 900+ employees from 30+ nationalities; 50% female leaders.
- **Interview process**: For science, product, and engineering roles: intro conversation → 2-5 technical exercises → 1-3 interviews (hiring manager + teammates) → values conversation → reference checks.

## Sources
1. [Mistral AI - About Page](https://mistral.ai/about/)
2. [Mistral AI - Careers Page](https://mistral.ai/careers/)
3. [Mistral AI - Homepage](https://mistral.ai/)
4. [CB Insights - Mistral AI Company Profile](https://www.cbinsights.com/company/mistral-ai)
5. [Mistral AI - LinkedIn](https://www.linkedin.com/company/mistralai)

## Other roles at Mistral

- [AI Scientist Intern - (Internship, Masters or Phd)](https://feeny.ai/job/ai-scientist-intern-internship-masters-or-phd-mistral-paris-43jzbe0kx4mv) — Paris, France
- [Engineering Manager, Serverless Containers](https://feeny.ai/job/engineering-manager-serverless-containers-mistral-paris-m06we4kkhq7s) — Paris, France
- [Engineering Manager, Fleet Delivery](https://feeny.ai/job/engineering-manager-fleet-delivery-mistral-paris-zsspnkk7y0k5) — Paris, France
- [Engineering Manager, Storage](https://feeny.ai/job/engineering-manager-storage-mistral-paris-ekf23bqg33ar) — Paris, France
- [Engineering Manager, Sandbox](https://feeny.ai/job/engineering-manager-sandbox-mistral-paris-5wx65405emb2) — Paris, France
- [Senior Engineering Manager, IaaS](https://feeny.ai/job/senior-engineering-manager-iaas-mistral-paris-n545rbk6r28j) — Paris, France
- [Forward Software Engineer](https://feeny.ai/job/forward-software-engineer-mistral-paris-gp4fe2vxk8pe) — Paris, France
- [Forward Software Engineer, Data](https://feeny.ai/job/forward-software-engineer-data-mistral-paris-5j7fnp825t2q) — Paris, France
- [Network Development Engineer, WAN & Edge](https://feeny.ai/job/network-development-engineer-wan-edge-mistral-paris-bb54t43jf8db) — Paris, France
- [Network Development Engineer, Data Center Fabrics](https://feeny.ai/job/network-development-engineer-data-center-fabrics-mistral-paris-3sgd968rfyhv) — Paris, France