Research Engineer, Responsible Frontier AI Research, DeepMind

main class="SxL7od" h2Requirements ul liBachelor's degree in Computer Science, Machine Learning, Mathematics, or a related technical field, or equivalent practical experience. li3 years of experience in Python programming. li3 years of experience with ML frameworks such as JAX, PyTorch, or TensorFlow. h2Preferred qualifications ul liMaster's degree or PhD in Computer Science, Engineering, or a related field with a focus on machine learning. liExperience in Python and C++ for high-performance ML library development. liExperience with harmful manipulation detection, persuasion modeling, deceptive behavior analysis, or AI safety evaluation and mitigation. liExperience working directly on AI safety, or responsible AI research. liExperience building evaluation frameworks, benchmarks, or automated testing pipelines for ML models. h2What you'll be doing ul liBe able to rapidly prototype and deliver scalable engineering solutions across the Responsibility research portfolio. liArchitect and optimize training and inference pipelines to detect and evaluate harmful manipulation behaviors in frontier language models. liDevelop post-training strategies to mitigate manipulation risks including deceptive persuasion, sycophancy, and covert influence tactics. liCollaborate with research scientists to translate safety research into robust implementations and present results to cross-functional stakeholders. liBuild and maintain evaluation infrastructure to systematically track model safety performance across releases. h2Perks and benefits ul liArtificial intelligence research at a pioneering AI lab. liInterdisciplinary teams focused on advancing AI for global challenges. liHigh-quality product innovation for billions of users. liUse of technologies for public benefit and scientific discovery. liVaried career pathways and learning opportunities.