As a Member of Technical Staff, Multimodal Safety, you will work to develop and implement cutting-edge safety methodologies for post-training multimodal large language models to be served to millions of users through Copilot every day. We work on the bleeding edge and leverage the most powerful pretrained models and algorithms, making it critical that we ensure our AI systems behave safely and align with organizational values. You will be responsible for designing novel safety evaluation frameworks, curating high-quality data for robust evaluations and training, prototyping new safety capabilities, and developing safety-focused fine-tuning algorithms. We're looking for outstanding individuals with deep expertise in multimodal AI safety who can translate research insights into practical solutions while being a strong communicator and collaborative teammate. The ideal candidate takes the initiative in exploring new safety methodologies and enjoys building world-class, trustworthy AI experiences in a fast-paced applied research environment.

Leverage expertise in multimodal safety to uncover potential risks and develop novel mitigation strategies, including alignment techniques and robustness improvements for multimodal large language models.

Create and implement comprehensive evaluation frameworks and red-teaming methodologies to assess model safety across diverse scenarios, edge cases, and potential failure modes.

Build automated safety testing systems, generalize safety solutions into repeatable frameworks, and write efficient code for safety pipelines and intervention systems.

Maintain a user-oriented perspective by understanding safety needs from user perspectives, validating safety approaches through user research, and serving as a trusted advisor on multimodal safety matters.

Track advances in multimodal safety research, identify relevant state-of-the-art techniques, and adapt safety algorithms to drive innovation in production systems serving millions of users.

Embody our culture and values.