Head of Cyber Safety

What you'll do

• Lead adversarial evaluations of frontier AI systems for offensive cyber capabilities and develop evolving cyber harm taxonomies.
• Partner with machine learning engineers to build benchmarks, classifiers, guardrails, detection systems, and evaluation infrastructure; advise on security risks and mitigations.
• Build and lead a cybersecurity team, establish evaluation processes, and represent the company with AI labs and security communities.

What they ask for

• Deep expertise in offensive cybersecurity, vulnerability research, exploit development, penetration testing, malware analysis, reverse engineering, or a related field.
• Significant experience assessing advanced cyber threats, offensive tooling, or AI-enabled cyber capabilities.
• Hands-on experience with adversarial evaluations, AI red-teaming, LLM security research, or evaluation datasets for frontier AI systems.
• Ability to work across cybersecurity research, AI safety, and machine learning engineering.

Nice to have

• Experience developing machine learning models, AI security classifiers, or automated cyber detection systems.
• Experience red-teaming frontier language models, jailbreaking, prompt injection research, or agentic AI evaluations.

Pay

$230,000 - $280,000 (base salary); $230K – $280K (base salary)

Tools

Python, Go, Rust

AI focus

Evaluates frontier AI systems for offensive cyber capabilities and develops benchmarks, safety infrastructure, guardrails, classifiers, and automated defenses.