Requirements

• Master's degree or PhD in Computer Science or a related technical field.
• Experience working on AI safety or responsible AI research.

Nice to Haves

• Master's degree or PhD in Computer Science, Engineering, or related field focused on Machine Learning.
• Experience in Python and C++ for high-performance machine learning library development.
• Experience with large language model demitigation, adversarial robustness, harmful manipulation detection, or AI safety evaluation and mitigation.
• Experience building evaluation frameworks, benchmarks, or automated testing pipelines for machine learning models.
• Prior direct experience in AI safety or responsible AI research.

What You'll Be Doing

• Prototype and deliver scalable engineering solutions across the Responsibility research portfolio.
• Architect and optimize training and inference pipelines to detect and evaluate harmful manipulation behaviors in frontier language models.
• Develop post-training strategies to mitigate manipulation risks such as deceptive persuasion, sycophancy, and covert influence tactics.
• Collaborate with research scientists to translate safety research into robust implementations and present results to cross-functional stakeholders.
• Build and maintain evaluation infrastructure to systematically track model safety performance across releases.

Perks and Benefits

• Work at a pioneering AI lab with interdisciplinary teams focused on advancing AI for global challenges and public benefit.
• Opportunities to collaborate with research programs worldwide and publish in the wider research community.
• Varied learning opportunities and career pathways within a large global organization.