Strategic Projects Associate, Safety

The Role

As a Safety Strategic Projects Associate (SPA), you will own the execution of large-scale human data programs that directly power frontier AI model training and evaluation. You will design, build, and execute operational workflows supporting model policy annotation and develop evaluations across a range of policy areas. You will use model policy annotation to help inform model training, evaluation, and enforcement decisions across leading AI systems.

Working hands-on with leading AI labs and technology companies, you will make real-time decisions that affect revenue, margins, delivery quality, 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.

What you'll do:

• Support the design and iteration of annotation frameworks and labeling workflows that scale while maintaining precision, accuracy, and inter-rater agreement
• Coordinate trusted annotators and contribute to a culture of consistency, care, and sound judgment when handling sensitive content and complex edge cases
• Partner with policy leads to organize and surface insights on policy gaps, classification ambiguities, and nuanced scenarios identified through annotation work
• Build and maintain detailed annotation playbooks, quality resources, and auditor guidance across diverse datasets and regulatory domains
• Analyze annotation data to identify emerging trends, systemic labeling errors, and opportunities to strengthen internal safety policies
• Work with frontier AI labs and internal stakeholders to support project scoping, issue resolution, and delivery of model policy programs

You Have

• A strong academic record as a recent graduate (or someone graduating soon), ideally with internship or light work experience in trust and safety, policy enforcement, regulatory compliance, risk management, management consulting, government, or a related field
• Strong analytical and first-principles problem-solving skills; comfort or aptitude for drawing insights from large datasets (SQL proficiency a plus)
• Excellent written and verbal communication skills, including the ability to work effectively with senior stakeholders and customers
• High ownership and a reliable, detail-oriented approach to execution
• Curiosity and an ability to quickly learn technical AI concepts and industry trends

Bonus Points

• STEM background or exposure to technical concepts (e.g., data, software, or AI)
• Experience supporting policy enforcement or content-review workflows across large, distributed workforces
• Familiarity with high-severity policy harms, including violent activities, dangerous organizations or individuals, or sexual activities
• Experience developing evaluations for harmful-content or policy-enforcement use cases

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.