Part-time contract work applying ML techniques to production systems (security, safety, RLHF) (Mercor, Handshake)
Other
Hands-on AI/ML security testing work applying machine learning techniques to production security and safety scenarios with an emphasis on RLHF-related evaluation. The engagement complements prior AI security coursework with practical implementation experience for AI safety and risk reduction. This work focuses on operationalizing AI security concepts rather than traditional data annotation. • Applies ML techniques in production (security, safety, RLHF) • Uses coursework-to-implementation approach to AI security testing • Supports evaluation of AI safety/risk behaviors in applied settings • Operates as part-time contract work while continuing education
2026 - Present