Job Description
📋 Description Own and pursue a research agenda for improving memory use and personalization in frontier models. Build robust evaluations for tracking modeling improvements. Design, implement, test, and debug code across our research stack. Collaborate with research and product teams to influence technical solutions in product. Work on reinforcement learning, dataset creation, evaluations, and other post-training methods. Contribute to a truly personalized ChatGPT experience across OpenAI products. 🎯 Requirements Background in frontier model post-training and product-driven research. Experience with user signals and human data for training/evaluation signals. Deep understanding of frontier model post-training and ML applications. Strong research craftsmanship and principled approach. Ability to navigate a large ML codebase and debug efficiently. Thrives in a fast-paced, technically complex environment. 🎁 Benefits Hybrid work model (3 days in office per week) in San Francisco, CA. Relocation assistance for new employees. Equity and competitive salary.
