Researching, building, and deploying AI/ML applications that solve real-world problems.
The world of Machine Learning and AI has always inspired me to explore how far we can push its boundaries. I love to research new ideas and continually challenge myself to learn and apply state-of-the-art techniques.
I hold a Bachelor’s in Computer Engineering from Pune University and am currently pursuing an M.S. in Computer Science at San José State University.
My hands-on experience spans Machine Learning and Deep Learning, with applications in Computer Vision, Natural Language Processing, and multimodal AI. Beyond AI, I’m proficient in full-stack development (MERN), cloud platforms (AWS), and orchestration tools (Docker, Kubernetes).
As a software engineer, I’m dedicated to building impactful applications that solve real-world problems. My focus is on advancing machine learning and multimodal AI, integrating these technologies to drive innovation and deliver value.
Led a team of 6 in developing a remote generator monitoring system with anomaly detection, remaining useful life prediction, and predictive maintenance models, achieving 93% accuracy on 500+ hours of operational data
Built an ANPR application using YOLOv11 and PaddleOCR with preprocessing pipelines, improving plate detection and text extraction to 97% accuracy
Eliminated 100% of manual intervention in LPG cylinder inspection by designing a ROS-based pre-filling pipeline with NVIDIA Triton Server, YOLO for defect detection, and EasyOCR for text extraction, producing 93% model
Automated an anomaly detection pipeline for copper coils by leveraging PatchCore and YOLO for defect identification and object tracking, with image compression to optimize performance
Engineered a real-time video streaming pipeline (Flask, React, Node.js, Express) with inference latency to 50ms, enabling smooth end-to-end deployment
Researched and evaluated pathfinding and collision avoidance algorithms for an autonomous boat navigation system
Built scalable computer vision systems including face recognition attendance (95% accuracy) and freezer space estimation (90% + accuracy, +30% efficiency), integrating with real-time pipelines
Engineered OCR and text-processing workflows for resume parsing, improving extraction accuracy by 85% and automating 70% of manual data entry
Developed and deployed YOLO models for industrial automation, achieving 92%+ detection accuracy and streamlining inventory tracking through end-to-end ML pipelines
A platform for connecting Fashion Models to Brand recruiters. Built with features like Job posting, searching, application, real-time chatting, online contract based hiring and much more.
Give colors to your black and white photographs using deep learning models
A tool designed to diagnose Lung cancer with the help of multi-omics data and CT scan images.
Roommate matching app that uses preference-based compatibility scoring to suggest the best fits.
Regression, Classification, Support Vector Machines, Decision Trees, Hidden Markov Models, Random Forest, Ensemble Learning, Dimensionality Reduction, Unsupervised Learning, Deep Learning, Computer Vision, Transformers, Auto-encoders & GANs, Natural Language Processing, RL Algorithms, Time series data analysis
TensorFlow, Keras, PyTorch, ROS, Scikit-Learn, NumPy, Pandas, Matplotlib, React, Express, Node.js, Next.js, Flask, spaCy, NLTK, LangChain, Streamlit
MySQL, SQL Alchemy, MongoDB, Mongoose, PostgreSQL, Prisma, Redis, AWS DynamoDB
AWS (EC2, RDS, Amplify, API Gateway, Cognito), Cloudflare, Git, Docker, Nginx, Kubernetes
Python, C++, JavaScript, TypeScript, Go, HTML/CSS