Applied Ai, Use-case, Software Engineer (harness)

Mistral AI Mistral AI · AI Frontier · Paris, France · Business

Software Engineer to build and productionize a cybersecurity product using AI. This involves orchestrating red-team/blue-team agent loops, developing context engineering for autonomous security workflows, and integrating with Mistral's corporate stack (Temporal-style orchestrator, Vibe) and models. The role requires building connectors, worker scaling, and SDKs to turn demos into production-grade services, enabling Applied to deploy at client sites and providing Science with infrastructure for training.

What you'd actually do

  1. Build and productionize the cyber harness and service prototype, turning research into deployable solutions
  2. Orchestrate red-team / blue-team agent loops: find vuln → patch → redeploy → re-test
  3. Develop the context engineering that enables autonomous security workflows
  4. Create connectors, worker scaling mechanisms, SDKs, and packaging that make demos into services
  5. Build on Mistral's corporate stack: Workflows (temporal-style orchestrator) and Vibe

Skills

Required

  • Strong software engineer
  • hands-on experience building cybersecurity products or tooling
  • Comfortable with agentic / LLM orchestration and context engineering
  • Builder mindset with a track record of shipping production-quality code
  • Experience with distributed systems and service architecture
  • Strong problem-solving abilities
  • attention to detail
  • Excellent communication skills
  • collaborative attitude

Nice to have

  • Red-teaming, offensive-tooling, or harness-building background
  • Experience with orchestration internals (Temporal, Workflows, or similar)
  • Prior experience building a "harness for X/Y use case in cybersecurity" or similar agent system
  • Infrastructure knowledge: containers & Kubernetes to move fast
  • Experience with AI/ML systems in security contexts
  • Contributions to open-source security or orchestration tools

What the JD emphasized

  • productionize
  • agent loops
  • autonomous security workflows
  • production infrastructure
  • production-quality code
  • agentic / LLM orchestration
  • harness for X/Y use case in cybersecurity

Other signals

  • productionize AI
  • agentic workflows
  • LLM orchestration
  • cybersecurity