Researcher, Multimodal Safety
$380k - $500k • San Francisco • FullTime
Posted 2mo ago
Job Location
San Francisco
Tech Stack
Remote Work Policy
On-site
Employment Type
FullTime
Categories
AI Research Engineer
About the job
OpenAI is seeking a Researcher for the Chat and Multimodal Safety team to advance the safety of frontier AI models across text, vision, and audio modalities. This role involves shaping how models perceive and reason about the world, translating that understanding into safe behavior, and developing research, training methods, and evaluations for multimodal safety. The ideal candidate will combine deep technical expertise with strong safety judgment, bridging perception and language, and have experience with vision-language models, modality fusion, or safety for multimodal systems.
Responsibilities
- Define and advance multimodal safety research for text, vision, and audio, connecting perception and semantic understanding to safe model behavior.
- Build training and evaluation methods for VLMs, including post-training, safety evals, and interventions for safe and appropriate model responses.
- Collaborate with other teams to translate research into safer ambient, embedded, and personalized multimodal experiences.
Requirements
- Track record of building or advancing multimodal models, with depth in vision-language models, video understanding, image generation, audio, or multimodal reasoning.
- Fluency across both perception and language.
- Understanding of multimodal systems end-to-end, including encoders, projection layers, modality fusion, cross-modal reasoning, scaling, and inference tradeoffs.
- Experience improving frontier model behavior through post-training methods like SFT, RL, data curation, synthetic data, evaluation, and error analysis.
- Strong research and engineering judgment for open-ended safety problems, including forming hypotheses, designing experiments, diagnosing failures, and translating findings into improvements.
Benefits
- Hybrid work model (3 days in office per week)
- Relocation assistance for new employees