Abhinav Sagar is a researcher with 7 years of experience at the intersection of computer vision and deep learning, currently working at imec in the Louvain area. His work focuses on visual reasoning, uncertainty quantification, and efficient neural architectures that make perception and decision-making more interpretable and robust in real-world systems. He has practical ML engineering chops from internships and industry roles—including computer vision engineering at Spyne and an ML internship at Instacart—and experience contributing to high-profile open-source projects like OpenAI Gym and mlpack, where he enhanced RL environments and Q-learning implementations. Comfortable across research and engineering, he combines C++ and JS contributions (e.g., p5.js) with academic training in robotics from the University of Maryland, enabling him to bridge prototype code and production-ready systems. An underappreciated strength is his track record of improving core environment implementations, reflecting attention to reproducibility and developer experience.
8 years of coding experience
2 years of employment as a software developer
Bachelor of Technology, Mechanical Engineering, Bachelor of Technology, Mechanical Engineering at Vellore Institute of Technology
Master of Engineering, Robotics, Master of Engineering, Robotics at University of Maryland
A toolkit for developing and comparing reinforcement learning algorithms.
Role in this project:
Back-end Developer
Contributions:1 review, 7 commits, 25 PRs in 2 months
Contributions summary:Abhinav primarily contributed to the environment files, implementing and modifying game environments within the OpenAI Gym library. Their work includes updating documentation, fixing constants, and adding constraints. They also modified the `car_racing.py`, `acrobot.py`, `pendulum.py`, `continuous_mountain_car.py`, and `mountain_car.py` files, indicating a focus on enhancing and improving the existing environments. This includes fixing errors and adding new features like the velocity goal constraint.
p5.js is a client-side JS platform that empowers artists, designers, students, and anyone to learn to code and express themselves creatively on the web. It is based on the core principles of Processing. Looking for p5.js 2.0? http://beta.p5js.org
Role in this project:
Full-stack Developer
Contributions:17 commits, 20 PRs, 10 comments in 2 months
Contributions summary:Abhinav contributed to the p5.js library by updating core JavaScript files such as `p5.Matrix.js`, `mouse.js`, and `p5.Element.js`, indicating a focus on the library's core functionality. They fixed typos in the `p5.Vector.js` test suite and modified the documentation-related `documented-method.js`, showing attention to code quality and developer experience. The user also updated linting configurations in `sample-linter.js` and made improvements to the test suite, demonstrating contributions across multiple aspects of the project.
jsp5jsjavascriptgraphicsart
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.