About Mistral

At Mistral AI, we believe in the power of AI to simplify tasks, save time, and enhance learning and creativity. Our technology is designed to integrate seamlessly into daily working life.

We democratize AI through high-performance, optimized, open-source and cutting-edge models, products and solutions. Our comprehensive AI platform is designed to meet enterprise needs, whether on-premises or in cloud environments. Our offerings include le Chat, the AI assistant for life and work.

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 France, USA, UK, Germany and Singapore. We are creative, low-ego and team-spirited.

Join us to be part of a pioneering company shaping the future of AI. Together, we can make a meaningful impact. See more about our culture on https://mistral.ai/careers.

Role summary

Embedded directly in a product team as search, chat, documents, or audio, you'll improve AI-powered features through rigorous evaluation, prompt and orchestration design, and rapid experimentation. You'll own your domain's AI quality end-to-end: define what "good" looks like, measure it, run experiments, and ship what works. Work with Science to deliver measurable improvements to quality, latency, safety, and reliability.

What you will do

• Design and run evaluations for your product area: reference tests, heuristics, model-graded checks tailored to search relevance, chat quality, document understanding, or audio performance.
• Define and track metrics that matter: task success, helpfulness, hallucination proxies, safety flags, latency, cost.
• Own prompt and orchestration design: write, test, and iterate on prompts and system prompts as a core part of your work.
• Run A/B tests on prompts, models, and configurations; analyze results; make rollout or rollback decisions from data.
• Set up observability for LLM calls: structured logging, tracing, dashboards, alerts.
• Operate model releases: canary and shadow traffic, sign-offs, SLO-based rollback criteria, regression detection.
• Improve core behaviors in your product area, whether that's memory policies, intent classification, routing, tool-call reliability, or retrieval quality.
• Create templates and documentation so other teams can author evals and ship safely.
• Partner with Science to diagnose regressions and lead post-mortems.

About you

• 3-4 years of experience; backgrounds that fit well include ML engineers moving closer to product, or software engineers with real AI/ML production experience.
• Strong TypeScript or Python skills - we have both tracks depending on team fit.
• Production LLM experience: prompts, tool/function calling, system prompts.
• Hands-on with evals and A/B testing; you can design metrics, not just run them.
• Comfortable implementing directly in product code, not only notebooks.
• Observability experience: logging, tracing, dashboards, alerting.
• Product mindset: form hypotheses, run experiments, interpret results, ship.
• Clear communication, autonomous, and oriented toward production impact over experimentation for its own sake.

It would be ideal if you also have:

• Safety systems experience: moderation, PII handling/redaction, guardrails.
• Release operations: canary/shadowing, automated rollbacks, experiment platforms.
• Prior work on search ranking, chat systems, document AI, or audio ML features.

Hiring Process

• Introduction call - 30 min
• Hiring Manager interview - 30 min
• Technical Rounds
  • Live-coding Interview - 45 min
• AI Engineering Interview - 45 min
• Culture-fit discussion - 30 min
• References