Back to jobs
Senior Staff Software Engineer, Agent Data Quality, DeepMind
Posted 2 weeks ago
Job Description
- Build a highly efficient agent data processing pipeline for user sentiment and behavior understanding and provide data insights and visualization systems.
- Build the experiment framework to evaluate agent and model performance to provide realtime feedback for the agent and model development.
- Construct rigorous quantitative benchmarks and automated evaluation frameworks (including LLM-as-a-judge) to measure agent capabilities in reasoning, planning, and tool use.
- Analyze agent behavior to identify failure modes, edge cases, and performance bottlenecks, turning these insights into actionable improvements.