Research Engineer: Multimodal RLHF & Personalized AI

OpenAI; San Francisco (CA); Hybrid; USD 380,000 - 445,000; Full time

Job summary

A leading AI research company in San Francisco is looking for a Research Engineer / Scientist to contribute to the Future of Computing Research team. The ideal candidate will develop methods for personalized AI systems, focusing on reinforcement learning and post-training. Strong machine learning experience is essential, along with a passion for building adaptive systems. This role utilizes a hybrid work model of four days in the office and offers relocation assistance for new hires.

Qualifications

• Strong background in machine learning with experience in RLHF.
• Experience with systems that must make high-quality decisions.
• Comfortable in building datasets or evaluation pipelines.

Responsibilities

• Develop RLHF and post-training methods for multimodal models.
• Build reward models and preference-learning pipelines.
• Design datasets capturing user preferences in realistic tasks.
• Run experiments on policy improvement using feedback.
• Collaborate with safety researchers for alignment and interpretability.

Skills

Machine learning

Reinforcement learning

Reward modeling

Preference optimization

Personalization

Human-in-the-loop evaluation

Job description

A leading AI research company in San Francisco is looking for a Research Engineer / Scientist to contribute to the Future of Computing Research team. The ideal candidate will develop methods for personalized AI systems, focusing on reinforcement learning and post-training. Strong machine learning experience is essential, along with a passion for building adaptive systems. This role utilizes a hybrid work model of four days in the office and offers relocation assistance for new hires.