Vaibhav Singh is a Sr. Data Scientist and Computer Vision engineer with ~8 years of experience building production-grade CV and ML systems, currently focused on vision-language models and generative AI. He has led curriculum and platform development at OpenCV University, created courses on GANs, diffusion models and face recognition, and is now driving a new VLM course while also working at Blackstraw. Vaibhav combines model training and fine-tuning (classification, detection, segmentation, VLMs) with production backend engineering using FastAPI, AWS, Celery and Nginx, and has built the OpenCV University Job Portal end-to-end. He actively maintains open-source projects—most notably porting popular vision models to Keras 3 with keras-vision—and contributes practical CV examples to repositories like learnopencv. His hands-on experience spans edge deployment tooling (NVIDIA DeepStream, DALI, Triton) and RAG systems, reflecting a focus on moving research into scalable products. Based in Chennai, he pairs strong academic performance (B.E. Computer Science, 9.20/10) with a penchant for technical writing and educational impact.
8 years of coding experience
5 years of employment as a software developer
Diploma in Computer Engineering, Computer Engineering, 84.31%, Diploma in Computer Engineering, Computer Engineering, 84.31% at Thakur Polytechnic
Bachelor of Engineering - BE, Computer Science, CGPA: 9.20 / 10, Bachelor of Engineering - BE, Computer Science, CGPA: 9.20 / 10 at University of Mumbai
Contributions:28 commits, 1 PR, 18 pushes in 2 years 7 months
Contributions summary:Vaibhav added a data science project focused on analyzing a Stack Overflow developer survey. The primary contribution involved creating and analyzing an interactive Jupyter Notebook. This included importing necessary libraries, loading and exploring the survey data, and potentially performing data cleaning, analysis, and visualization to extract meaningful insights from the survey responses.
Contributions:12 commits, 12 PRs, 3 comments in 3 months
Contributions summary:Vaibhav added assets and implemented custom document segmentation using PyTorch and DeepLabV3. This involved preparing a dataset, defining a segmentation dataset class, and training a model with a specified architecture. The user also utilized libraries like OpenCV, and applied random grayscale transformations for data augmentation.
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.