Machine Learning Manager, Red Teaming - Responsible AI and Safety

What you'll do

• Lead and develop a team of red-teaming engineers with sustained ownership over specific feature clusters.
• Establish an independent red-teaming agenda focused on active vulnerability discovery rather than standard evaluation.
• Manage the coverage strategy for pre-ship qualification, post-ship monitoring, and foundation model red-teaming.
• Define division of responsibility and escalation paths with adjacent security teams regarding cross-cutting risks.
• Manage external red-teaming partnerships to expand program coverage and integrate them into existing pipelines.
• Provide technical direction for the development of automated red-teaming capabilities.
• Define, instrument, and report on red-teaming success metrics to leadership on a recurring basis.

What we're looking for

• MS or PhD in Computer Science, Machine Learning, Statistics, or a related field.
• Experience working with generative models for evaluation and product development.
• Strong engineering skills and experience writing production-quality code in Python.
• Deep experience in foundation model-based AI programming and prompt optimization.
• Experience working with noisy, crowd-based data labels and human evaluations.
• Publication record in relevant conferences such as NeurIPS, ICML, ICLR, or EMNLP.
• Experience working on Responsible AI and AI Safety.
• Strong organizational and operational skills for managing large, multi-functional teams.