LinkedIn · Kaggle · victor.tsai.info@gmail.com
4+ years in software engineering — now building at the intersection of data science and ML. I specialize in data pipelines, statistical modeling, and applied ML, with a backend foundation that lets me ship end-to-end. Strong at translating ambiguous business problems into measurable outcomes.
Targeting: Data Scientist · ML Engineer · Analytics Engineer
AI Agent – Open Data Knowledge Base (2026 – present)
RAG + SQL hybrid agent that auto-generates API requests and wrangles open datasets for research — targeting 50% reduction in dataset discovery time.
Anomaly Detection for Wearable Devices (2025)
Unsupervised anomaly detection on 3,000-user time-series logs with no ground truth. K-out-of-3 model agreement via linear mixed model ensembling.
ASU Displaced Voice — Eviction Analysis (2025)
K-means + linear mixed-effects model on Maricopa County census data to identify statistically significant drivers of eviction case increases.
ML / Data: Python pandas scikit-learn PyTorch R SQL PySpark Tableau
Backend / Infra: PostgreSQL MongoDB Docker Git REST APIs