AI Security Platform & Automation Engineer

Compensation: competitive (Contract-to-FTE path with equity/benefits)

We're an AI security startup automating cyber defense to help organizations defend against the accelerating and increasingly dangerous cyber capabilities of AI. We deploy agents across enterprises to find and automatically fix the highest-priority vulnerabilities.

As part of this mission, we also contribute to frontier AI security research, working with partners to understand dangerous capabilities in cybersecurity and AI control.

What you'll do

• Build realistic IT and ICS/OT environments for testing and evaluating AI agents
• Design and run evaluations of agent capabilities - metrics, ground-truth scorers, and methodology
• Turn open-ended research questions into working systems and reproducible results
• Contribute to frontier research on dangerous cyber capabilities and control

Must-haves

• Strong programming, automation, and infrastructure skills, especially building realistic environments with containers, VMs, networking, and Linux/Windows internals
• Hands-on experience building and evaluating AI agents (tool-use, scaffolding, multi-step autonomy)
• Comfort with evaluation and benchmarking frameworks (e.g. Inspect), designing metrics, building ground-truth scorers, interpreting results, and iterating on methodology
• Ability to work independently in an ambiguous, fast-moving environment

Nice-to-haves

• Practical cybersecurity depth in offensive or defensive operations
• Familiarity with enterprise IT, or ICS/OT and industrial protocols
• Interest in AI safety, security, or control research

Contract

We are looking for immediate part- or full-time support.

We would prefer if you are based in a similar timezone, but we are open to anyone.

How To Apply‍

Please send your CV and describe a project you've built that you're proud of, ideally one relevant to AI agents, evaluations, or security.

careers@0labs.ai