New York jobs

Strategic Projects Lead, Safety

HandshakeNew York, NYFull-timeOn-site2+ years experience

$160k/yr listed by the employer

Looks real. 1 thing to check before you apply.

On Handshake’s own careers site (Ashby), checked open today.

  • To check: Posted by the employer 2 months agoLong-open jobs are sometimes already filled. Ask when they plan to hire.
  • Checked: On the company's own careers siteAshby board
  • Checked: Checked open todayAshby board
  • Checked: Pay listedJob posting
  • Checked: No reposts foundAshby board
  • Trust score 89 / 100 · Looks good
See all 6 checksShow fewer
How we check

What you’ll do

  • Own red-teaming and safety evaluation programs from scoping through delivery, across multiple frontier AI labs and policy domains.
  • Design and run adversarial tests, including jailbreak development, push-to-failure testing, and evaluations of models using tools and multi-step autonomy.
  • Lead expert testing teams and adapt staffing, training, skill mix, and incentives to maintain precision and delivery reliability.
  • Work with AI lab policy leads to identify coverage gaps and emerging risks, and synthesize findings into reports and policy and evaluation recommendations.

Summarised from the posting by AI and can be wrong. The full description is the source.

Requirements

Experience

  • 2+ years of experience in trust & safety, red-teaming, security research, policy enforcement, or a related technical/analytical field
  • Experience red-teaming, jailbreaking, or adversarially evaluating LLMs or agentic AI systems (preferred)
  • Subject matter expertise in high-severity policy harms (e.g., CBRN, cyber, violent extremism) (preferred)
  • Experience running testing or evaluation programs (preferred)
  • Background in security research, offensive security, or AI safety research (preferred)

Skills

  • Excellent project and workforce management skills
  • Working familiarity with adversarial testing concepts (jailbreak techniques, prompt-based exploits) or a fast ability to pick them up
  • Curiosity and ability to quickly learn technical AI concepts, model behavior, and industry trends

Other requirements

  • High ownership mindset with pride in end-to-end accountability
  • Exposure to sensitive or explicit content (e.g., violent, sexual, or otherwise disturbing material) as part of safety and policy evaluation work

Your match

Sign in and add your resume to see which of this job's requirements it shows.

Sign in to check your match

Saved to your account, encrypted. The AI that reads it doesn't keep it or train on it.

Benefits

Health insurance
Medical coverage and mental health support
Dental & vision
Dental and vision coverage
Retirement plan
401(k) match
Paid time off
Flexible PTO, 15 holidays, and 2 flex days
Parental leave
Paid parental leave
Equity
Equity in a fast-growing company
Bonus
Competitive compensation
Learning & tuition
$2,000 learning stipend and ongoing development
Remote work stipend
Internet and commuting benefits; free lunch and gym in the San Francisco office
Wellness & mental health
$500 wellness stipend
Family & fertility support
Fertility benefits and parental coaching
Other
Financial coaching, Team outings and referral bonuses

Full job description

From Handshake’s careers site

ABOUT HANDSHAKE

Handshake was founded on a simple belief that everyone deserves a path to a great career, regardless of where they went to school or who they know. Today, we power 25 million job seekers, 1 million+ employers, and 1,600 educational institutions.

In 2025, we started Handshake AI and built the fastest-growing AI data business in history. We work directly with frontier AI lab researchers to create evaluations, publish benchmarks, and push the boundary of data. We’ve grown from $0 to ~$1B run rate and pay ~$60M to over 30K individuals every month.

Why join Handshake now:

Show full descriptionShow less
  • Shape how every career evolves in the AI economy, at global scale, with impact your friends, family and peers can see and feel
  • Partner hand-in-hand with world-class AI labs, Fortune 500 partners and the world’s top educational institutions
  • Work together with engineers, scientists, operators, and more from Palantir, Meta, Scale AI, and former YC founders
  • Build a massive, fast-growing business with billions in revenue

About Handshake AI

Human data is the core infrastructure to AI advancement. Frontier AI labs currently improve model capabilities with various data-intensive post-training techniques. We believe that data spend for AI training will increase by 3-5x in the next few years and continue for much longer as models take on new domains. Handshake AI supports all of the frontier AI labs, working on their most complex data at the largest scale.

THE ROLE

As a Strategic Projects Lead (SPL) on AI Safety & Red Teaming, you will own the execution of large-scale adversarial testing programs that directly develop frontier AI models before and after release. You will design and run structured efforts to push models to failure, spanning work such as evaluating harm and policy categories against frontier labs’ own policy specifications, developing jailbreak and adversarial technique pipelines, and extending red-teaming into agentic settings, among other methods, then work directly with frontier labs to turn what you find into sharper policies and stronger evaluation coverage.

Working hands-on with leading AI labs, you will make real-time decisions that affect delivery quality, program scope, and long-term customer relationships. This is a high-ownership, outcomes-driven role for operators who thrive in ambiguity, move fast with incomplete information, and are accountable for results at scale.

  • Own end-to-end execution of red-teaming and safety evaluation programs spanning sensitive, high-severity harm categories, from scoping through delivery
  • Run multiple programs across different frontier labs and policy domains, each with its own scope, harm categories, and stakeholders
  • Design and run adversarial testing methodologies, such as jailbreak technique development and iterative push-to-failure testing, to surface model vulnerabilities against frontier labs’ policies
  • Extend red-teaming methods into agentic contexts, evaluating how models behave under adversarial pressure when operating with tools and multi-step autonomy
  • Lead and coordinate teams of expert Fellows executing sensitive, high-stakes testing work, maintaining precision and consistency across harm categories, languages, and markets
  • Partner directly with policy leads at frontier AI labs to identify coverage gaps, ambiguous classifications, and emerging risk areas, and help shape policy documents based on findings
  • Synthesize testing data into insight reports that surface trends, systemic gaps, and recommended areas of policy and evaluation development
  • Design and adapt staffing models for your red-teaming workforce (team size, skill mix, training, and incentive structures) to improve throughput and delivery reliability as program requirements evolve

YOU HAVE

  • 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, comfortable leading and directing teams of red-teamers and testers against tight timelines and shifting scope
  • Strong analytical and first-principles problem-solving skills, comfortable operating in ambiguous, fast-changing testing environments
  • 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, including with senior customers and policy teams at frontier AI labs
  • High ownership mindset with pride in end-to-end accountability
  • Curiosity and ability to quickly learn technical AI concepts, model behavior, and industry trends

BONUS POINTS

  • 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

Note: 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.

WE OFFER

Handshake delivers benefits that help you feel supported—and thrive at work and in life. The below benefits are for full-time US employees.

🎯 Ownership: Equity in a fast-growing company 💰 Financial Wellness: 401(k) match, competitive compensation, financial coaching 🍼 Family Support: Paid parental leave, fertility benefits, parental coaching 💝 Wellbeing: Medical, dental, and vision, mental health support, $500 wellness stipend 📚 Growth: $2,000 learning stipend, ongoing development 💻 Remote & Office: Internet, commuting, and free lunch/gym in our SF office 🏝 Time Off: Flexible PTO, 15 holidays + 2 flex days 🤝 Connection: Team outings & referral bonuses

Explore our mission, values, and comprehensive US benefits at joinhandshake.com/careers http://joinhandshake.com/careers.

Something wrong with this job? Report it · This flag looks wrong

Similar jobs

Strategic Projects Lead

Handshake · San Francisco, CA +1 place

$160k/yrFull-timeOn-site

Looks goodChecked open todayPosted 16 days ago

Strategic Projects Lead, Coding

Handshake · San Francisco, CA +1 place

$172k–$204k/yrFull-timeOn-site

Check details2 to checkChecked open todayPosted 6 months ago

Strategic Insights Manager

Handshake · San Francisco, CA +1 place

$130k–$165k/yrFull-timeHybrid

Looks goodChecked open todayPosted 24 days ago

See more like this