CareerPlanGet AI match score →

Technical Program Manager – Adversarial Model Research

San Francisco💼 Full-time🗓 2026-01-26 → 2026-07-31

Core

Lead initiatives to test the safety and robustness of OpenAI's models through creative experimentation and structured evaluation to mitigate risks in advanced AI systems.

Role type

Technical Program Manager (AI Safety & Adversarial Research)

Builds

Research programs for model safety, robustness evaluations, and red-teaming campaigns

Domain

Artificial Intelligence / Large Language Models / AI Safety

Deliverable

research

Required skills

Technical program management, organizational skills, communication, familiarity with large language models, prompt engineering, model evaluation techniques, managing high-uncertainty projects, creative problem solving, cross-functional coordination

Preferred skills

Experience in technical program management, familiarity with LLMs and evaluation techniques, ability to shape projects from ground up, creativity in testing methods

Technologies

Large language models, prompt engineering frameworks, model evaluation tools

Responsibilities

Lead programs exploring unexpected model behaviors and identifying failure modes; Translate vague risk signals into clear priorities and actionable research plans; Design and run creative evaluations, experiments, and red-teaming campaigns; Collaborate with research, product, and deployment teams to integrate findings into model training and deployment cycles; Develop repeatable systems for tracking model performance and understanding emerging behavior patterns

Seniority

Individual Contributor, mid-to-senior level

Sourced via ashby · Listed on CareerPlan, which tracks 70,000+ jobs from 20+ sources.
Apply on Ashby ↗