Computer Engineering Student · AI/ML Builder
GenAI · RAG · Computer Vision · Reinforcement Learning
Building useful AI systems, not just demos.
Computer Engineering student building applied AI systems across GenAI, RAG, computer vision, and reinforcement learning.
I like projects where AI does a real job: analyst, retriever, inspector, evaluator, or game agent.
| Project | Focus | What it does |
|---|---|---|
| DataPilot AI | GenAI + Data Analytics | Turns CSV files into dashboards, analyst chat, insights, exports, and predictions |
| VidContext RAG | RAG | Lets users ask questions over YouTube transcripts with timestamp citations |
| SiteGuard AI | Computer Vision | Detects PPE compliance and safety violations from construction-site images |
| DeviceLens | Agentic Vision | Inspects phone condition from images and generates a condition report |
| HireLens | GenAI + ATS | Compares resumes with job descriptions and builds improvement roadmaps |
| Game AI Lab | RL / Game AI | Reinforcement-learning and search agents for 2048, Bluff, UNO, Barricade, and more |
Open project notes
Autonomous CSV analytics workspace with schema profiling, data-quality checks, adaptive dashboards, grounded AI analyst chat, exportable reports, and prediction tools.
Full-stack YouTube transcript RAG app with timestamped chunks, ChromaDB retrieval, grounded answers, and source inspection.
Construction-site PPE detection system using YOLO, FastAPI, and React. Detects hardhats, safety vests, workers, violations, machinery, and vehicles.
Agentic phone-condition inspection app that validates phone images, detects visible damage, applies deterministic scoring, and optionally explains results with GPT.
Resume-to-job matching system that parses resumes and job descriptions, scores fit, identifies missing skills, and returns practical roadmaps.
{
"languages": ["Python", "JavaScript", "TypeScript", "HTML", "CSS"],
"ai_ml": ["PyTorch", "TensorFlow", "scikit-learn", "OpenCV", "Ultralytics YOLO"],
"gen_ai": ["OpenAI API", "RAG", "Embeddings", "ChromaDB", "Prompt Engineering"],
"backend": ["FastAPI", "Flask", "Node.js", "Express"],
"frontend": ["React", "Next.js", "Vite", "Tailwind CSS"],
"databases": ["SQLite", "JSON stores", "Local vector stores"],
"workflow": ["Git", "GitHub", "Local-first apps", "Portfolio-grade prototypes"]
}- Strengthening ML and deep learning fundamentals
- Building cleaner AI/ML portfolio projects
- Improving DSA and problem-solving with Python
- Learning how to design systems that are useful, not just flashy
