AI Engineer, Product

Mistral AI Mistral AI · AI Frontier · Paris, France · Engineering & Infra

AI Engineer focused on improving AI-powered product features through evaluation, prompt/orchestration design, and experimentation. This role owns AI quality end-to-end for a product area, working with Science to deliver measurable improvements.

What you'd actually do

  1. 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.
  2. Define and track metrics that matter: task success, helpfulness, hallucination proxies, safety flags, latency, cost.
  3. Own prompt and orchestration design: write, test, and iterate on prompts and system prompts as a core part of your work.
  4. Run A/B tests on prompts, models, and configurations; analyze results; make rollout or rollback decisions from data.
  5. Set up observability for LLM calls: structured logging, tracing, dashboards, alerts.

Skills

Required

  • TypeScript
  • Python
  • Prompt engineering
  • Orchestration design
  • A/B testing
  • Metrics definition
  • LLM observability
  • System prompts

Nice to have

  • Safety systems experience
  • Moderation
  • PII handling/redaction
  • Guardrails
  • Release operations
  • Canary/shadowing
  • Automated rollbacks
  • Experiment platforms
  • Search ranking
  • Chat systems
  • Document AI
  • Audio ML features

What the JD emphasized

  • 3-4 years of experience
  • Strong TypeScript or Python skills
  • Production LLM experience
  • Hands-on with evals and A/B testing
  • Comfortable implementing directly in product code
  • Observability experience
  • Product mindset

Other signals

  • Improve AI-powered features through rigorous evaluation, prompt and orchestration design, and rapid experimentation.
  • 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.