Latest AI JobsBrowse Jobs
Handshake logo

Strategic Projects Lead, Safety

HandshakeNew York, NYHAI Delivery Ops
Apply on company site
Salary
$160K USD
Job type
Full-time
Posted
16 Sept 2026
Status
Open · checked 7d ago

About this role

This Strategic Projects Lead, Safety position at Handshake offers a hands-on opportunity to run large-scale adversarial testing programs for frontier AI models in New York, NY. This role suits experienced operators with a background in trust, safety, or security research who thrive in fast-paced environments.

Role Overview

Handshake is hiring a full-time Strategic Projects Lead to join the HAI Delivery Ops department in New York, NY. In this position, the individual will take complete ownership of executing large-scale adversarial testing programs to develop frontier AI models before and after release. The professional will design structured efforts to push models to failure, evaluate harm categories against specific policies, develop jailbreak pipelines, and extend red-teaming into agentic settings. Collaborating directly with leading AI labs, the lead will make real-time decisions impacting delivery quality, program scope, and customer relationships.

Key Responsibilities

Own the end-to-end execution of red-teaming and safety evaluation programs covering sensitive harm categories from scoping to delivery.
Manage multiple programs across different frontier labs and policy domains with unique scopes and stakeholders.
Design and run adversarial testing methodologies, such as jailbreak technique development and push-to-failure testing, to uncover model vulnerabilities.
Extend red-teaming methods into agentic contexts to evaluate model behavior under adversarial pressure during multi-step autonomy.
Coordinate teams of expert Fellows executing sensitive testing work while maintaining precision across languages and markets.
Partner directly with frontier AI lab policy leads to identify coverage gaps, clarify ambiguous classifications, and refine policy documents.
Synthesize testing data into insight reports highlighting trends, systemic gaps, and recommendations.
Design and adapt staffing models for the red-teaming workforce to enhance throughput and delivery reliability.

Requirements

Possess a minimum of 2 years of experience in trust and safety, red-teaming, security research, policy enforcement, or a related technical or analytical field.
Demonstrate excellent project and workforce management skills with the ability to lead testers against tight timelines.
Exhibit strong analytical and first-principles problem-solving skills suited for ambiguous, fast-changing environments.
Maintain working familiarity with adversarial testing concepts like jailbreak techniques and prompt-based exploits, or the ability to learn them quickly.
Offer exceptional communication and stakeholder management skills to work with senior customers and policy teams.
Demonstrate a high ownership mindset and absolute accountability for results.
Show curiosity and a capacity to rapidly learn technical AI concepts and industry trends.
Note that this position involves exposure to sensitive or explicit content, including violent, sexual, or disturbing material, as part of standard policy evaluation duties.

Nice to Have

Prior experience red-teaming, jailbreaking, or adversarially evaluating large language models or agentic AI systems.
Subject matter expertise in high-severity policy harms such as CBRN, cyber threats, or violent extremism.
Experience managing testing or evaluation programs.
Professional background in security research, offensive security, or AI safety research.

Skills and Tools

Adversarial testing and jailbreak technique development
Prompt-based exploit analysis
Workforce and project management
Stakeholder management and policy enforcement
Analytical reporting and synthesis of testing data

Salary and Benefits

Annual salary of $160,000 USD
Equity in a fast-growing company
Financial wellness perks including a 401(k) match, competitive compensation, and financial coaching
Family support features such as paid parental leave, fertility benefits, and parental coaching
Comprehensive medical, dental, and vision health coverage, mental health support, and a $500 wellness stipend
Professional growth provisions featuring a $2,000 learning stipend and ongoing development
Flexible PTO, 15 holidays, and 2 flex days
Internet and commuting support, team outings, and referral bonuses

About the Company

Handshake powers millions of job seekers, employers, and educational institutions with a mission to ensure everyone deserves a path to a great career. The organization works closely with frontier AI lab researchers to build data businesses, create evaluations, and publish benchmarks.

How to Apply

Candidates interested in this opportunity should apply directly on the official Handshake careers page at joinhandshake.com/careers.

Questions candidates ask

What is the salary for the Strategic Projects Lead, Safety role?

The annual salary for this full-time position is $160,000 USD.

Where is this job located?

This role is located in New York, NY and is not a remote position.

How much experience is required to apply?

Applicants must have 2 or more years of experience in trust and safety, red-teaming, security research, policy enforcement, or a related technical or analytical field.

What kind of content will I be exposed to in this role?

This role involves exposure to sensitive or explicit content, such as violent, sexual, or otherwise disturbing material, as a routine part of safety and policy evaluation work.

What benefits are offered for this position?

US full-time employees receive company equity, a 401(k) match, paid parental leave, medical/dental/vision coverage, a $500 wellness stipend, a $2,000 learning stipend, flexible PTO, and 15 holidays plus 2 flex days.

How do I apply for this position?

You can apply by visiting the official Handshake careers page at joinhandshake.com/careers.

Ready to apply?

The application is on the official Handshake careers page.

Apply on company site