I'm an AI/ML researcher and engineer — a B.Tech Artificial Intelligence student (2023–2027) working on deep learning for energy and physical systems: building models that respect the physical laws of the real world, not just fit the data.
I'm the second of five authors on an IEEE APPEEC 2026 paper on physics-informed load forecasting — presented in Singapore, forthcoming in IEEE Xplore — as part of my ongoing research on power-grid forecasting and grid optimization (the Watt-IF project, which includes learning-based grid-partition policies).
What I work on
- 🔬 Research — physics-informed & constrained ML, and time-series forecasting
- 🧠 ML / DL — model design, training, benchmarking, and optimization in Python, PyTorch, TensorFlow, scikit-learn
- ⚙️ Systems & backend — REST APIs and scalable services with Node.js, Express, NestJS, MongoDB
I care about clean engineering, honest collaboration, and problem-solving at scale, and I'm currently deepening my foundations in NLP, computer vision, and system design. Competitive programming is a constant thread that keeps my algorithmic and mathematical problem-solving sharp.
📫 Open to research collaborations and opportunities in AI/ML.
