Memory & RL Research Engineer — Hybrid SF, Relocation

OpenAI; San Francisco (CA); Hybrid; USD 180,000 - 230,000; Full time

Benefits offered by this job

Relocation assistance

Job summary

OpenAI's Personalization-Memory team in San Francisco seeks a Research Engineer/Research Scientist to advance memory architecture, post-training methods, and long-horizon evaluations for frontier models.

You will push RL research, translate rigorous findings into product impact, build robust evaluations, and collaborate across research and product teams in a hybrid role with relocation assistance.

Qualifications

• Background in reinforcement learning research and ability to translate findings into product impact.
• Ability to iterate quickly and work across a large ML codebase.
• Comfortable operating in a fast-paced, technically complex environment.

Responsibilities

• Own and pursue a research agenda for improving memory in frontier models.
• Build robust evaluations to track modeling improvements.
• Design, implement, test, and debug code across the research stack.
• Collaborate with research and product teams to shape technical solutions.

Skills

Reinforcement learning

Research iteration

Product impact focus

Job description

OpenAI's Personalization-Memory team in San Francisco seeks a Research Engineer/Research Scientist to advance memory architecture, post-training methods, and long-horizon evaluations for frontier models.

You will push RL research, translate rigorous findings into product impact, build robust evaluations, and collaborate across research and product teams in a hybrid role with relocation assistance.