Computer Science Engineering student at SOA University, interested in AI/ML, backend development, and building practical software systems.
I mostly work with Java and Python, and I'm currently spending most of my time getting better at DSA, backend engineering, and deploying ML applications.
AegisExtract — Privacy-preserving medical document processing using FastAPI, Tesseract OCR, and local Llama 3 inference. The entire pipeline runs locally through Docker.
DemandSense AI — Retail demand forecasting system combining a PyTorch LSTM with Prophet and business-rule guardrails, with a Streamlit dashboard for exploring forecasts and inventory impact.
LedgerGuard — Event-driven fraud detection pipeline built around Java, Kafka, FastAPI, and XGBoost. Transactions are streamed through Kafka and evaluated by an ML service in real time.
Languages: Java, Python
AI / ML: PyTorch, Scikit-learn, Prophet, XGBoost
Backend: FastAPI, REST APIs, Apache Kafka
Data: Pandas, NumPy
Tools: Docker, Git, GitHub
I'm working through DSA and Java fundamentals while building projects around backend systems and machine learning.
I'm particularly interested in how ML models move beyond notebooks and become reliable software — APIs, data pipelines, containers, and eventually cloud infrastructure.