Applied AI, Use-case, Software Engineer (Harness)
Apply at source. Mistral AI handles the application directly; Houtini doesn't take a fee from candidates or companies. We curate which companies appear; the listings come from yubhub.
What the team is looking for.
We are seeking strong Software Engineers with cybersecurity experience to build and productionize our cybersecurity product offering. You will turn cutting-edge prototypes into robust, scalable services that power both our offensive and defensive security capabilities.
Cyber Harness Productionization
- Build and productionize the cyber harness and service prototype, turning research into deployable solutions
- Orchestrate red-team / blue-team agent loops: find vuln → patch → redeploy → re-test
- Develop the context engineering that enables autonomous security workflows
- Create connectors, worker scaling mechanisms, SDKs, and packaging that make demos into services
Mistral Stack Integration
- Build on Mistral's corporate stack: Workflows (temporal-style orchestrator) and Vibe
- Work with containers/Kubernetes to deploy and scale cyber capabilities
- Leverage Mistral Models to power agentic security workflows
- Migrate existing prototypes onto our production infrastructure
Service Engineering
- Design and implement the engineering foundation that enables Applied to deploy at clients
- Create the infrastructure Science can train against for continuous improvement
- Ensure the cyber harness is robust, scalable, and maintainable
- Collaborate with security and engineering teams to integrate cyber capabilities
About you
- Strong software engineer with 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 and attention to detail
- Excellent communication skills and collaborative attitude
It would be ideal if you also 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
- cybersecurity
- software engineering
- agentic/LLM orchestration
- context engineering
- distributed systems
- service architecture
- problem-solving
- communication
- collaboration
- red-teaming
- offensive-tooling
- harness-building
- orchestration internals
- Temporal
- Workflows
- containers
- Kubernetes
- AI/ML systems
- open-source security
Other roles you might consider.
Filtered through the same AI-companies allowlist.
Regional Vice President (RVP) of Solution Architecture
Cursor
Regional Director, Forward Deployed Engineering
Cursor
Regional Director, Forward Deployed Engineering
Cursor
Engineering Manager, Identity & Access Platform
OpenAI
Technical Deployment Lead - UAE
OpenAI
Software Engineer - Networking Software and Services
xAI
New to AI work? Start with these.
Six pieces of orientation. Most AI-company job specs assume you've done this kind of hands-on work already. If you haven't, an afternoon with one of these is the cheapest way to close the gap.
Claude Desktop, from zero.
The agentic-AI assistant most of the people you'd be working alongside use every day. Install, configure, first useful prompts.
What MCPs areThe best MCPs for Claude Desktop.
MCP servers extend an AI assistant with tools and data. The catalogue most teams use. Useful technical context for any AI-engineering role.
Code with AIClaude Code, the complete beginners' guide.
The CLI for AI-paired development. Required reading if you're applying for any engineering role that mentions agents, or any role full stop.
Run a local modelHow to set up LM Studio.
Running a model on your own machine teaches you more about how AI products work in three hours than a year of using ChatGPT will.
The hardware realityBeginner's guide to AI hardware.
What the infrastructure under the model actually looks like. Useful context for infrastructure, applied-AI and hardware roles.
Browse the stackMCP catalogue.
Eleven MCP servers Houtini maintains or recommends. Each detail page describes a real piece of working AI infrastructure.