Research Program Manager - Model Evals and Safety

Reflection - New York, NY

Hiring: Research Program Manager - Model Evals and Safety Company: Reflection Location: New York, NY Job Posted Time: 2026-09-13 17:59:14 Employment Type: Full-time Target Skills & Keywords: Model Evaluations, AI Safety, Research Program Management, Evaluation Frameworks, Red-Teaming, Alignment Research, ML Engineering, Safety Operations, Cross-functional Leadership, 0-to-1 Program Building Experience: - 7+ years of experience in technical program management, research operations, or ML engineering - Demonstrated experience standing up new functions, teams, or programs from scratch - Familiarity with the landscape of model evaluation and AI safety, including evaluation methodologies, red-teaming, alignment research, and the evolving regulatory and industry landscape Required Skills: - Ability to bring clarity to ambiguity and drive decisions when the path forward is unclear - Strong cross-functional partnership skills with research and engineering leads across pre-training, mid-training, and post-training - Experience defining evaluation frameworks, tooling requirements, and operational processes - Ability to scope and prioritize eval science and eval infrastructure investments - Experience establishing engagement with external safety ecosystems, including third-party assessments, academic partnerships, and industry safety frameworks - Strong reporting and communication skills to give leadership clear visibility into model safety status, evaluation coverage, and open risks - First-responder mentality with the ability to jump in, assess situations, cut through noise, align stakeholders, and drive resolution Qualifications: - High-leverage leader and operator who can embed directly with research and infrastructure teams - Not a project tracker — a force multiplier who connects work across multiple teams into a coherent whole - Comfortable with 0-to-1 work, building foundational infrastructure and processes from the ground up - Champions a culture of blameless post-mortems and continuous learning Compensation: Not specified Interested candidates, please apply directly through the job posting on company's career page or try via AI auto apply on this platform. Don’t miss this opportunity to join a forward-thinking team!