I build intelligent systems that solve real-world problems. With expertise in deep learning, computer vision, and NLP, I'm passionate about pushing the boundaries of AI research and innovation.
I am a passionate Machine Learning Engineer currently pursuing my Master's degree in AI/ML. With a strong foundation in mathematics and programming, I specialize in developing innovative solutions using cutting-edge AI technologies.
My research interests include deep learning, computer vision, generative AI and natural language processing. I'm constantly learning and exploring new technologies to stay at the forefront of AI innovation.
Symbiosis Institute of Technology, Pune
2024 - Present
DIEMS, Aurangabad
2020 - 2023
My projects & contributions
A comprehensive sentiment analysis application that analyzes text input or CSV files to predict sentiment (positive, negative, or neutral). Built with Python and Flask for backend and Next.js for the frontend, featuring interactive visualizations of sentiment distribution.
An advanced anomaly detection system for CNC milling machines using deep learning. Leverages autoencoder neural networks to analyze tri-axial vibration data and identify potential machine performance issues in real-time with 85% F1 score.
An innovative AI system for real-time analysis of water pollution in the Ganga River. Combines YOLOv8, U-Net, and AlexNet in a multi-model framework to detect, segment, and classify polluted areas from drone imagery with high precision.
An advanced solution for detecting marine oil spills using Automatic Identification System (AIS) data and Sentinel-1 SAR satellite imagery. Combines vessel anomaly detection through DBSCAN clustering with U-Net-based image segmentation to enable rapid and accurate oil spill monitoring with exceptional precision metrics.
John Deere India Pvt. Ltd.
Jun 2025 - Dec 2025
Applied computer vision models (YOLO, DETR, ViT, SAM2, Grounding DINO) to automate processes, saving 4+ hours per task and improving efficiency. Fine-tuned large language models on custom image datasets, boosting accuracy by 50% and reducing hallucinations. Built a speech-to-text pipeline with Whisper and GPT-4o, cutting manual typing by 2 hours and improving transcription accuracy by 10%. Designed and deployed multi-agent workflows with Graph Neural Networks on AWS, streamlining document processes and enhancing LLM reliability.
KSJ Technology Pvt Ltd
Feb 2023 - Feb 2024
Led data analysis initiatives by creating and maintaining Power BI dashboards for recruitment metrics that provided actionable insights to optimize hiring strategies. Performed comprehensive data cleaning and analysis using Excel and Python to ensure accurate reporting, while automating key workflows that improved efficiency by 20%. Collaborated with cross-functional teams to streamline recruitment data pipelines, ultimately enhancing the organization's decision-making processes.
thorveomkar4@gmail.com
+91 8999424867
Pune, India