CV
Contact
| Name | Yifan Yang |
| Title | Research Assistant | M.Sc. in Artificial Intelligence and Robotics |
| yifanyang6@link.cuhk.edu.cn | |
| Location | Shenzhen |
| Website | yifanyang6.github.io |
| Profiles | GitHub · ORCID |
Summary
Research assistant advised by Prof. Pinjia He and M.Sc. student working at the intersection of AI for Software Engineering and AIOps, with a focus on microservice diagnostics, observability, and AI-assisted troubleshooting.
Experience
-
Aug 2024 - Present Shenzhen
Research Assistant
The Chinese University of Hong Kong, Shenzhen
- Work under the supervision of Prof. Pinjia He at the School of Data Science.
- Conduct research in AI for Software Engineering and AIOps, with an emphasis on microservice diagnostics, root cause analysis, observability, and fault-propagation-aware evaluation.
- Contribute to end-to-end research workflows across multiple projects, including system implementation, telemetry and data collection, fault injection, system integration, baseline reproduction, and performance evaluation.
- First author of Gleaner, an online sampling framework for microservice diagnostics accepted at ISSTA 2026.
Education
-
Sep 2024 - Present Shenzhen
M.Sc.
The Chinese University of Hong Kong, Shenzhen
Artificial Intelligence and Robotics
- School of Data Science.
-
Sep 2019 - Jun 2023 Jinan
B.Mgt.
Shandong University
Industrial Engineering
- Training in systems thinking, optimization, and engineering practice.
Publications
-
Apr 2026 Gleaner: A Semantically-Rich and Efficient Online Sampler for Microservice Diagnostics
Accepted at ISSTA 2026
-
Oct 2025 -
Oct 2025 DynaCausal: Dynamic Causality-Aware Root Cause Analysis for Distributed Microservices
Under peer review (ASE 2026 submission)
-
2024 Metis: An Interpretable and Unified Troubleshooting Framework for Microservices using Multi-modal Data
Under review at ACM Transactions on Software Engineering and Methodology (TOSEM)
* Corresponding author
Projects
- Gleaner — Diagnosis-oriented online trace sampling for microservice observability.
- chaos-experiment — Fault injection tooling for microservice troubleshooting experiments.
- Aegis — Experiment tooling and systems engineering workspace for AIOps research.
Skills
Research Areas: AI for Software Engineering, AIOps, microservice diagnostics, root cause analysis, observability
Systems: Linux, Docker, Kubernetes, Helm, Skaffold, OpenTelemetry, Jaeger
Programming: Python, Go, Shell, SQL
ML and LLM: PyTorch, vLLM, LLM fine-tuning, inference optimization
Languages: Chinese (Native), English (IELTS 6.5)