Computer Vision Engineer

Master's in Computer Vision and 5+ years of computer vision industry experience.

VLMs Computer Vision Deep Learning Research Image Processing Video Anaytics Azure Cloud HPC MLOps

What I Bring to the Table

Cutting Edge CV

Expertise in MLLMs, training, finetuning LLMs, stable diffusion models, LoRA

Classical Computer Vision

Expertise in object detection, image segmentation, and facial recognition using OpenCV and YOLO.

Deep Learning

Proficient in CNN and RNN architectures with TensorFlow and PyTorch for real-world applications.

Research

During my master's, I gained hands-on experience applying research methodologies, exploring novel ideas, and leveraging HPC resources to train/eval large-scale models.

Image Processing

Skilled in classical techniques for enhancement, restoration, and feature extraction.

Azure Cloud

Experience deploying ML models and APIs using Azure AI and Cognitive Services.

Projects

Retail Analytics System

Dynamic Scene Graph Generation(DSGG)

Use Multi-Modal Large Language Models for generating DSG, zero-shot as well as finetuning

Retail Analytics System

DistilledDino

Distilled DINO models to smaller efficientnets and VITs for efficient inference.

Retail Analytics System

RetailEye

Built a real-time customer behavior analysis system using YOLO and OpenCV, preventing self checkout theft.

EEG Visualization

EEG Visual Stimuli

EEG research is my passion. I'm resrarching how we can interpret our brain singals that can read our thoughts and visulize our dreams. I have developed algorithms to convert EEG signals into visual representations for brain-computer interfaces.

Security System

Drunk and Drowsiness Alert System(DADAS)

Implemented a drunk and drowsiness alert system for long route drivers for monitoring and safety purposes.

Professional Experience

Research Assistant

Center for research in computer vision @UCF | May 2024 - Jan 2025

Neurosymbolic AI based approach to generate Dynamic Scene Graph from videos using Off-the-shelf MLLMS(Multi-Modal Large Language Models)

Individual Contributor

UCF College of Medicine | Dec 2023 - Apr 2024

Designed CV algorithm to perform angle measurement of MRI data(DICOMs) for the bone alignment using Segment Anything Model(SAM) + Image Classifier Heads

Systems Engineer

Tata Consultancy Services(TCS) | June 2018 - June 2023

Over my five years at TCS, I had the opportunity to take on diverse roles and contribute to various projects, including leading a team of two in developing computer vision solutions. This experience laid a strong foundation in software engineering and corporate best practices, while also exposing me to real-world challenges in computer vision.

Academics

Master's in Computer Vision

University of Central Florida | August 2023 - May 2025

Focused on advanced computer vision techniques and emerging research, bridging theory with real-world applications.

Cutting-Edge Research

What can off-the-shelf MLLMs do for Dynamic Scene Graph Generation?

Proposed a novel approach for dynamic scene graph generation using off-the-shelf multi-modal large language models (MLLMs), outperforming state-of-the-art methods at Top-1, Top-5, and Top-10 accuracy while effectively balancing the precision-recall tradeoff.

EEG Signal Analysis & Visualization

Developing novel algorithms to transform brain activity into actionable visual data, with applications in neuroscience and human-computer interaction.

Let's Connect

I'm open to opportunities and collaborations in computer vision and AI. Reach out to discuss ideas or projects!