Hi, I'm Vijay Vignesh

Machine Learning Engineer

I build scalable ML and LLM systems with real-time computer vision, RAG pipelines, and autonomous agents. I deliver high-performance, cost-efficient models across the full lifecycle and contribute to open-source tools that enhance reliability and context-aware intelligence.

Profile Picture of Vijay Vignesh

About Me

I build production-ready ML and LLM systems that deliver real impact, from real-time computer vision to autonomous agents and RAG pipelines. I enjoy working on challenging problems and transforming research ideas into deployable solutions.

I contribute to open-source projects, experiment with new ML architectures, and explore the latest trends in AI and software development.

$2M+

Total Annual Business Savings from Efficiency & Performance Improvements

10K+

Hours of Model Training & Experimentation

10+

Open-Source Contributions

3

Papers Published & Patent Granted

Experience

Machine Learning Engineer

Gentex Corporation | 2023 - Present

  • I design and optimize end-to-end machine learning systems, including large language models and RAG pipelines, enhancing model efficiency and reducing inference latency.
  • Leading initiatives to improve real-time reliability, delivering production-grade ML solutions that drive measurable business outcomes, including $1M+ in annual cost savings.
  • Optimized model inference, latency, and compute usage across full ML lifecycle: data → training → optimization → deployment → monitoring.
  • Collaborating with cross-functional teams to advance technology, optimize workflows, and improve operational efficiency.

Research Assistant

International Institute of Information Technology | Glosys Technology | 2019 – 2022

  • Developed novel 3D hand and body pose estimation and image captioning models, contributing to multiple publications and conference presentations.
  • Implemented and benchmarked deep learning architectures (ResNet, Transformers, CRNN) for computer vision and NLP tasks.
  • Built synthetic datasets and pipelines for efficient model training, evaluation, and deployment on GPUs and cloud infrastructure.
  • Collaborated in multi-disciplinary research teams to produce high-impact solutions for real-world ML problems.

Software Development Engineer

Dell Technologies | 2018 - 2019

  • Developed network automation and testing tools using Python, improving operational efficiency by over 80%.
  • Integrated software with network engineering requirements and streamlined deployment pipelines.
  • Worked on real-time data processing systems and contributed to codebase optimizations for performance.

Skills & Technologies

Machine Learning & AI

PyTorch TensorFlow Transformers RAG Pipelines Computer Vision Deep Learning Object Detection Object Tracking

Data & Engineering

Python SQL AWS Docker Linux API Development ETL Pipelines Distributed Systems

Core ML Libraries

PyTorch PyTorch Lightning TensorFlow NumPy SciPy Transformers

Featured Projects

CustomOCR Project Screenshot

Lightweight OpenPose MobileNet for Real-Time Hand Keypoint Detection (PyTorch)

This project implements a lightweight OpenPose MobileNet architecture in PyTorch for real-time hand keypoint detection. Inspired by the paper “Real-time 2D Multi-Person Pose Estimation on CPU: Lightweight OpenPose”, the model leverages the Hands from Synthetic Data (CMU) dataset, which provides 21 keypoints per hand image.

OpenPose PyTorch Computer Vision Hand Keypoint Detection
Monocular 3D Hand Pose Estimation Project Screenshot

Monocular 3D Hand Pose Estimation with ResNet (PyTorch)

This project implements a monocular 3D hand pose estimation model using a ResNet-based architecture in PyTorch. The model is trained on the FreiHAND dataset, which follows the MANO parametric hand model format, enabling seamless integration with SMPL-X or SMPL-H body models.

PyTorch Computer Vision 3D Hand Pose Estimation
CustomOCR Project Screenshot

CustomOCR: End-to-End OCR Training Pipeline (PyTorch & Lightning)

CustomOCR is a complete OCR training pipeline built with PyTorch and PyTorch Lightning, enabling fast and efficient dataset generation, preprocessing, and model training.

OCR PyTorch Lightning Synthetic Data

Get In Touch

Let's work together!

If you’d like to collaborate, share insights, or just say hi, I’d love to hear from you.

vijayvigneshp02@gmail.com
Grand Rapids, Michigan, USA