Staff Software Engineer - Agent Quality

Job Description

As a Staff Software Engineer - Agent Quality, you will design and scale the infrastructure and tooling for evaluating Databricks' AI Agents. You will also build a feedback loop that connects evaluation results back into agent improvement throughout the development lifecycle.

Requirements: Candidates should have 6+ years of industry experience in building software systems and strong Python programming skills. Experience with distributed systems and the ability to design reliable systems are also essential.

Key Skills: Python, Distributed Systems, Data Pipelines, Large-Scale Infrastructure, Reliability, Correctness, Operational Maturity, Evaluation, Benchmarking, Regression Detection, Quality Measurement, Devtools, CI/CD, Testing Frameworks, Observability Tooling, LLM