🚀 Software Engineer + ML/AI Engineer building systems that turn data into reliable, real-world decisions.
My work focuses on backend systems, distributed data processing, and applied machine learning—especially where ML models need to operate within scalable, production-grade infrastructure.
- ⚡ High-performance systems (C++, multithreading, low-latency design)
- 🔄 Distributed data pipelines (Kafka, Spark, real-time processing)
- 🧠 ML/AI systems (deep learning, time-series, retrieval + GenAI)
- 🌐 Backend services and APIs for production deployment
- Crop yield prediction (<10% error)
- River discharge forecasting (0.95 NSE, <5% error)
- Flood mapping (>90% accuracy)
- Retrieval + GenAI systems combining structured + semantic search
I focus on deploying ML systems—not just training models:
- data pipelines
- validation
- integration with backend systems
- Concurrent key–value store (C++) → 7.7M ops/sec
- Real-time analytics pipeline → 59K events/sec
- Scalable APIs and microservices
I use LLM-assisted workflows to accelerate development, while maintaining full ownership of system design, correctness, and performance.
C++, Python, Kafka, Spark, PostgreSQL, FastAPI, Docker, Linux, PyTorch