A Full Stack Developer and AI/ML Engineer who builds end-to-end intelligent systems — from scalable backend architectures and real-time APIs to machine learning pipelines, computer vision models, and generative AI applications. I turn complex problems into production-ready solutions.

< skills />
Tools are just a means to an end — but I've honed my craft with these specific instruments.
< projects />
Advanced ML pipeline for high-precision time-series forecasting using ensemble methods.
Offline-capable real-time monitoring dashboard for wastewater management with multi-category anomaly detection, automated model retraining, and predictive output estimation.
Domain-specific RAG system for construction documentation with hybrid search, streaming responses, and context-aware chat history management — built on Flask and LangGraph.
Conversational AI voice agent that autonomously conducts inbound travel sales calls, qualifies leads with a conversion confidence score, and seamlessly hands off to human agents when needed.
Intelligent AI voice agent for insurance intake that conducts structured customer calls, qualifies prospects, scores conversion likelihood, and routes complex cases to human advisors.
Gmail-style AI email client that connects via IMAP, auto-categorizes incoming mail, flags urgent messages, generates contextual replies, and applies a configurable rule engine for intelligent inbox management.
Hybrid ML recommendation engine for wine discovery, combining collaborative filtering, content-based filtering, and behavioral signals like order and search history for highly personalized suggestions.
Scalable backend system for a feature-rich community platform with real-time messaging, hierarchical group structures, role-based permission management, recurring events, and low-latency architecture powered by Redis, PostgreSQL, and AWS.
HIPAA-compliant full stack healthcare platform with 4 distinct roles, infinitely nestable staff hierarchies, concurrent multi-role session management, and end-to-end prescription and refill workflows.
Local vision LLM-powered harmful content detection system that classifies images and video frames into threat categories like weapons and nudity, with aggregated reasoning and detailed response output.
Deep learning pipeline trained on Detectron2 to detect and measure kitchen elements from architectural elevation drawings — combining elevation detection, OCR-based dimension extraction, pixel-to-real-world scaling, and NMS-based conflict resolution.
< experience />
From writing my first model to leading production ML systems — here's the journey.
Engineered and delivered production-grade systems across multiple client domains — including a HIPAA-compliant multi-role healthcare platform, a real-time community and chat backend, a kitchen element detection pipeline using Detectron2, a harmful content classifier with local vision LLM inference, a wastewater anomaly detection system, and a hybrid wine recommendation engine. Work spans full-stack development, ML pipelines, computer vision, and generative AI.
Worked as a software engineering intern during the second year of undergraduate studies, gaining hands-on industry exposure in software development workflows, codebase practices, and collaborative engineering.
Led the Machine Learning and Software division of the university robotics club for two years. Mentored junior members, organized technical workshops, directed software and ML projects, and drove the club's technical vision across robotics and AI initiatives.
Completed Bachelor of Technology in Electronics and Communication with a strong focus on Artificial Intelligence, Machine Learning, and Software Engineering. Graduated in 2024 while simultaneously leading the university robotics club and building real-world AI systems.
< contact />
Whether it's a complex ML system, a data pipeline, or an AI product — let's talk and make it happen.