As a Staff Software Engineer - Agent Quality at Databricks, you will be a key member of a new team dedicated to enhancing the quality of AI Agents. Your primary focus will be on building and scaling the infrastructure and tools necessary for rigorous evaluation and improvement of these agents. You will work closely with researchers and engineers to ensure that evaluation results effectively inform agent development. This role offers the opportunity to shape the technical direction of agent quality infrastructure within the company.

• 6+ years of industry experience building software systems
• Strong Python programming skills with experience in production or research infrastructure
• Experience building or operating distributed systems, data pipelines, or large-scale infrastructure
• Ability to design systems that produce trustworthy and reproducible signals for complex applications
• Comfort working across ambiguous research and product boundaries

• Establish the foundational evaluation infrastructure for Genie Agents to enable rigorous benchmarking and quality measurement.
• Build a feedback loop that connects evaluation results back into agent improvement.
• Influence the long-term technical direction for agent quality infrastructure.
• Collaborate with both research and product teams to enhance agent development.