The Research Engineer position at DeepMind focuses on advancing agent quality through the development of evaluation systems and data flywheels for Google's Gemini Spark. The role involves collaborating with interdisciplinary teams to tackle real-world problems in artificial intelligence and machine learning. Engineers will contribute to foundational research while also engaging with the wider research community. The Agent Quality team aims to enhance tool-using capabilities for frontier agents, ensuring continuous improvement and innovation.

• 2 years of experience with agentic AI workflows, frameworks, and approaches.
• 1 year of experience with machine learning and deep learning.
• Experience in software engineering and cloud-based development.
• Experience with Python, TensorFlow, PyTorch, or similar ML frameworks.

• Design, build, and scale realistic agent environments and task suites.
• Research and develop Agentic AutoRaters, calibrating them against human evaluation.
• Enable agents to automatically generate and iterate on verifiers to facilitate effective exploration.
• Develop trajectory analysis frameworks and diagnostic tooling to identify root-cause agent failure modes.
• Harvest complex multi-turn interaction trajectories into high-quality datasets and reward signals.

• Employees at Google are often offered benefits like comprehensive health insurance, 401(k) matching, and flexible work arrangements, among other benefits.