About this role
The Agentic Ops US team focuses on two major areas: Code Graph and Quality Validation. The code graph serves as the data foundation for validation, encompassing static relationships (function calls, experiment/instrumentation dependencies) and dynamic execution paths (reconstructed from traces). Quality validation covers static rule checking (mining soft and logical constraints) and dynamic issue detection, reproduction, and fixing. We aim to improve code reliability and R&D efficiency through systematic, data-driven approaches.
Responsibilities
- Design, develop, and optimize Code Graph capabilities, including static relationship extraction, dynamic trace processing, execution path reconstruction, and graph data modeling.
- Design and develop static validation capabilities based on the code graph, including mining and validating logical and soft constraints, while continuously improving rule accuracy and coverage.
- Contribute to the development of dynamic validation systems for production issue detection, reproduction, root cause localization, and assisted fixing, and build reusable solutions for common scenarios.
- Conduct in-depth analysis of complex production quality issues, leveraging code, traces, and other runtime signals to identify root causes, distill reusable validation patterns, and drive automation coverage.
- Explore and introduce cutting-edge techniques in code analysis, program slicing, anomaly detection, LLMs/Agents, and related areas, and apply them to real-world engineering problems.
- Collaborate closely with engineering and infrastructure teams to drive the adoption of Code Graph and Quality Validation capabilities in real development workflows and production scenarios.