Building ML systems for science and production: diffusion models, LLM agents, weather forecasting, genomics NLP.
Not from a CS background. Taught myself ML, shipped code upstream, earned PyTorch org recognition.
B.Tech @ NIT Rourkela '27 | CGPA 8.02 | Odisha, India
|
|
|
|
|
|
| Project | What it does | Highlights |
|---|---|---|
| Weather Transformer | Physics-aware ViT for 6-hour weather forecasting on ERA5 data | From scratch in PyTorch, 74 tests, beats persistence baseline by 27% |
| Neural-LAM Analysis | Deep research into probabilistic weather forecasting with GNNs | Forward pass analysis, training flow study, loss function mechanics |
| LLaMA Task Agent | LoRA fine-tuned LLaMA-3.1-8B for agentic tool execution | Generates valid function calls with type-safe args from natural language |
| Complaint Intelligence | RAG pipeline over 15K+ consumer complaints | FAISS vector search + Gemini, Streamlit deployment |
| MalariaGEN NLP | Natural language to malariagen_data API translation |
10/10 test queries, 7 API methods covered |
| Bio Publication Analyzer | SciBERT + TF-IDF classifier for genomics articles | 81 tests, 99.5% F1 on Europe PMC data |
