Forward Software Engineer, Data

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.

About The Job
As a Forward Software Engineer, Data, you will build the systems behind some of the hardest problems Mistral takes on. You join our team of engineers in Applied AI. We gravitate towards hard problems, decide how to solve them, and ship fast. You work closely with our customer-facing teams, and what works goes into production with our customers and across the company. When a project needs it, you work directly on customer engagements. We're looking for a strong software engineer who builds end to end and has shipped ML or GenAI systems to production. You've felt the pain of models that pass every eval and fail on real data, and of quality that drifts after launch. You've also felt the data engineering pain: pipelines that break silently, schemas that change under you, and backfills that take a weekend. Data engineering is your edge. You turn messy, large-scale data into systems that hold up. You think like a founder. You start from the customer's problem, not the technology. You measure success by the value you deliver, and you care about building experiences people love to use. You like working at the edge of what AI can do today, and you push past it. Your scope is end to end, from first prototype to production. Your depth in data architecture helps set the standard for how the team designs and delivers systems. You know lakehouse and data mesh patterns well enough to know when they fit and when they're overkill. You've designed ontologies and data models, and you know that getting them right is as much art as science.

What you will do
Build AI systems end to end, from first prototype to production.

Design the data architecture underneath them: ingestion, processing, storage, and the data models and ontologies that make messy data usable.

Build distributed pipelines that process large volumes of documents, code, logs, and multimodal content for retrieval, agentic workflows, and fine-tuning.

Turn what works for one customer into patterns and platforms that work across many, without rebuilding each time.

Make systems hold up under real load: throughput, latency, cost, and failure recovery are part of the design from the start.

Build data governance into the systems themselves: ownership, access control, lineage, retention, and privacy for sensitive enterprise data.

Build the evaluation loop: labeling with LLMs and humans, versioned eval datasets, and checks that catch quality drift before customers do.

Set the standard for how the team designs and ships data systems.

Work with researchers, engineers, and customer-facing teams to turn hard problems into systems people rely on.

What We're Looking For
You have full ability to ship across the stack: proficient NodeJS e.g. NextJS/Express/Fastify or similar or Python e.g. FastAPI. You are confident with TypeScript + React/NextJS or similar. Solid beats polished.

You have 5+ years of experience building and running production data-intensive pipelines with distributed processing (for example Spark, Ray, Beam, or Dask) and orchestration tools (for example Airflow, Dagster, or Prefect) with structured and unstructured data.

You have experience with retrieval-augmented generation, agentic use cases, or LLM evaluation, and a clear view of how data quality drives model quality.

You