Strategic Projects Lead - AI Safety

What you'll do

• Scope client safety and data problems, manage delivery from initial discussion through final output, and drive revenue.
• Recruit and lead specialist contributors, ensuring high-quality work.
• Design safety datasets, benchmarks, taxonomies, and repeatable human and automated red-teaming methodologies.

What they ask for

• 2+ years in AI safety, red teaming, trust & safety, adversarial ML, or security research, at a frontier AI lab, FAANG, top security firm, or equivalent.
• Hands-on adversarial experience, such as model jailbreaking, prompt injection research, offensive security, penetration testing, bug bounty, CTFs, or trust & safety investigations.
• Fluency in harm taxonomies, evaluation design, safety frameworks, and model policy.
• Python proficiency and ability to write production-quality code.

Nice to have

• Published safety, alignment, or security research; or success in bug bounty, CTF, or model red-teaming competitions.
• Experience building automated red-teaming or evaluation pipelines, working in a high-consequence risk domain, or using AI tools to automate workflows and build products.

Pay

$150K – $225K (base salary)

Tools

Python

AI focus

Develops adversarial datasets, jailbreak and attack taxonomies, refusal-boundary and over-refusal sets, safety benchmarks, and repeatable human and automated red-teaming methods for frontier models.