Data Engineer | MS Applied Data Intelligence @ San Jose State University
Building data pipelines, ML systems, and backend infrastructure. Focused on streaming architectures, computer vision, and distributed systems.
Computer vision pipeline for soccer video analysis. Multi-model tracking with YOLO detection, ByteTrack, and GraphSAGE embeddings served via FastAPI.
Stack: YOLO • ByteTrack • GraphSAGE • FastAPI • MLflow • Docker
Detection and segmentation experiments for sports analytics. Benchmarks with RF-DETR, SAM2, and SigLIP architectures.
Stack: PyTorch • RF-DETR • SAM2 • SigLIP • Weights & Biases
Screenshot capture with OCR and LLM-powered context retrieval. Semantic search over personal knowledge base.
Stack: Python • LLMs • OCR • PostgreSQL • FastAPI
Graph neural networks for molecular property prediction. PyTorch Geometric implementation for structure analysis.
Stack: PyTorch Geometric • GNNs • Molecular Chemistry
Web archiver with change detection. Tracks content modifications and maintains versioned snapshots.
Stack: Python • Web Scraping • Data Archival
Languages
ML & Computer Vision
Data Engineering
Backend & DevOps
Open to: Data Engineering, ML Infrastructure, Backend roles