jobs

Research Scientist - Multimodal Agent, Consumer Devices

About the TeamThe Future of Computing Research team is an applied research team within the Consumer Devices group focused on developing new methods, models, and evaluation frameworks that support our vision for the future of computing. We w

In inglese

Company

OpenAI

Location

San Francisco

Status

Open

Posted

2026-07-21T15:27:05.038+00:00

OpenAI's Future of Computing Research team, within Consumer Devices, is hiring a research scientist or engineer for RLHF and post-training of personalized, multimodal systems. The work covers reward modeling, preference learning, dataset and rubric design, long-horizon evaluation, and policy improvement using explicit feedback, implicit signals and model-based grading, with close collaboration with safety researchers. The posting asks for an ML research background in RLHF, reward modeling, preference optimization or post-training, plus experience in reinforcement learning, ranking, recommenders, personalization or human-in-the-loop evaluation. Hybrid in San Francisco, with relocation assistance.