Strategic Projects Lead, Safety

The role

You will own the execution of large-scale adversarial testing programs to develop frontier AI models. You will design and run structured efforts to push models to failure and work with frontier labs to improve policies and evaluation coverage.

What you will do

• Own end-to-end execution of red-teaming and safety evaluation programs.
• Run multiple programs across different frontier labs and policy domains.
• Design and run adversarial testing methodologies.
• Extend red-teaming methods into agentic contexts.
• Lead and coordinate teams of expert Fellows.
• Partner directly with policy leads at frontier AI labs.
• Synthesize testing data into insight reports.
• Design and adapt staffing models for the red-teaming workforce.

Required qualifications

• 2+ years of experience in trust & safety, red-teaming, security research, policy enforcement, or a related technical/analytical field
• Excellent project and workforce management skills
• Strong analytical and first-principles problem-solving skills
• Working familiarity with adversarial testing concepts (jailbreak techniques, prompt-based exploits) or a fast ability to pick them up
• Exceptional communication and stakeholder management skills
• High ownership mindset
• Curiosity and ability to quickly learn technical AI concepts, model behavior, and industry trends

Nice to have

• Experience red-teaming, jailbreaking, or adversarially evaluating LLMs or agentic AI systems
• Subject matter expertise in high-severity policy harms (e.g., CBRN, cyber, violent extremism)
• Experience running testing or evaluation programs
• Background in security research, offensive security, or AI safety research

Benefits

• Equity in a fast-growing company
• 401(k) match
• Competitive compensation
• Financial coaching
• Paid parental leave
• Fertility benefits
• Parental coaching
• Medical, dental, and vision
• Mental health support
• $500 wellness stipend
• $2,000 learning stipend
• Internet, commuting, and free lunch/gym in our SF office

Before you apply

• This role involves exposure to sensitive or explicit content (e.g., violent, sexual, or otherwise disturbing material) as part of safety and policy evaluation work.

About the company

Handshake powers 25 million job seekers, 1 million+ employers, and 1,600 educational institutions. Handshake AI works directly with frontier AI lab researchers to create evaluations, publish benchmarks, and push the boundary of data.