01 / Flagship system
ConceptGraph AI
Course-aware GraphRAG that turns PDFs into searchable concept graphs, reranks evidence, and returns page-grounded answers.
8/10 Expected page @5 · baseline
Loading the archive…
Working products first. Each case study connects the implementation to its decisions, evidence, and limitations.
Course-aware GraphRAG that turns PDFs into searchable concept graphs, reranks evidence, and returns page-grounded answers.
A PostgreSQL-backed job runner that makes retries, worker crashes, lease recovery, and cancellation visible—with Python and Go workers.
Lap-time prediction and Monte Carlo simulation for comparing pit-stop strategies using real 2021–2025 F1 data.
A mood-aware journaling and conversation product designed around secure personal data, recent context, and restrained AI assistance.
Parses résumés locally, scores five ATS dimensions, compares job descriptions, and exports actionable feedback.
A timetable-planning concept. The public repository currently contains a README and license, not an implemented scheduler.
Internship work at Bluestock: analysis across 40 schemes, 10 datasets, 87K+ records, and 4.5 years of NAV history.
A PhiUSIIL dataset investigation covering preprocessing, baseline models, Optuna tuning, and saved inference artifacts.