resume
General Information
| Full Name | Albert (Geyang) Xu |
| albertxu1010@gmail.com | |
| Phone | 858-568-6771 |
| Website | albertgy9910.github.io |
| Location | Los Angeles, CA |
Research Interests
- Data-centric robustness of ML pipelines
- ML/MLOps reliability & monitoring
- Responsible & transparent data management
- Streaming & distributed data systems
- Data provenance & explanations
- Governance of ML systems
Education
-
2026.09 - Expected Ph.D. in Computer Science (Incoming)
University of California, Riverside - Riverside, CA
-
2022.09 - 2024.03 Master of Science in Computer Science
University of California, San Diego - GPA: 3.88/4.0
- Courses: Operating Systems, Networks, Programming Languages, ML, Probabilistic Modeling, Data Ethics
-
2018.09 - 2022.06 Bachelor of Science in Computer Science
University of Liverpool, UK - GPA: 3.93/4.0 (top 3%)
Experience
-
2025.10 - 2026.04 Software Engineer
Fuyao Glass America Inc. - Built a YOLOv8 computer-vision pipeline for inline automotive-glass inspection, detecting scratch, chip, edge, and coating defects on line-camera frames.
- Integrated detections into Python/SQL ETL with coating/tempering/inspection data; shipped role-based dashboards for OEE, FPY, scrap, and changeover.
- Productionized CV inference + ETL with cron, alerts, and access control — 99.3% job success and 2.4 hrs/week less downtime; supported A/B and DOE setpoint studies in Jupyter.
-
2024.10 - 2025.10 Software Engineer
4Pexonic Inc. - Developed an academic impact analysis platform tracking citation patterns across tens of thousands of records using Node.js, MongoDB, and Next.js with Docker, serving university researchers and policy institutions.
- Built two-tier caching (in-process LRU + Redis), cutting median and p95 latency by 40%.
- Integrated gRPC microservices; implemented bcrypt/session auth and Nginx TLS.
-
2023.10 - 2024.10 Research Engineer
UCSD Halıcıoğlu Data Science Institute - Built modular Python Injector pipeline (generate → sample → inject → eval) with beam-search + Optuna/TPE, cutting downstream AUC by >0.25 vs. random attacks.
- Co-authored SAVAGE (PVLDB'25), designing corruption dependency graphs and bi-level black-box search to model mechanism-aware missingness, selection-bias, and outlier patterns for pipeline-level stress-testing of ML systems.
- Ran Inject → Clean → Retrain benchmarks across missing-value, selection-bias, and outlier scenarios to evaluate state-of-the-art cleaning, debiasing, and UQ pipelines and expose their data-centric robustness gaps.
Publications
-
2025 Stress-Testing ML Pipelines with Adversarial Data Corruption (SAVAGE)
PVLDB 18(11): 4668–4681 (2025) - {"Preprint"=>"https://arxiv.org/abs/2506.01230"}
- {"Code"=>"https://github.com/lodino/savage"}
Skills
-
Programming Languages
- Python, Java, Go, SQL, C/C++, JavaScript, R
-
Frameworks and Tools
- Docker, Git, gRPC, Node.js, Next.js, Django, React, MongoDB, Optuna, Jupyter, YOLOv8, AWS