Sanskar Agrawal
Machine Learning Engineer at Meta
London, England, United Kingdom
Summary
🤩
Rockstar🎓
Top SchoolSanskar Agrawal is a Machine Learning Engineer with nine years of experience building computer vision and 3D ML systems, currently at Meta London after leading ML at Preimage. He blends deep research expertise from IIT Kharagpur with hands-on engineering, having driven open-source development for Open3D-ML and contributed tensor API demos, image I/O, and tests to a widely used 3D data library. His work spans photogrammetry, NeRF-based 3D reconstruction, multi-view stereo, and real-time Gaussian splat rendering for browser-based 360° imagery, reflecting a focus on both academic rigor and deployable systems. At Intel Labs he produced a novel dataset and a Mitsuba-based relighting baseline that outperformed prior methods and earned an oral presentation at 3DV. Comfortable in C++, Python, and OpenCV, he pairs production-minded engineering with research leadership across perception stacks integrating sensors like IMUs, lidar, and stereo cameras.
9 years of coding experience
8 years of employment as a software developer
Bachelor of Technology (B.Tech.) Electrical Engineering, Bachelor of Technology (B.Tech.) Electrical Engineering at Indian Institute of Technology, Kharagpur
Stackoverflow
1reputation
0reached
0answers
0questions
Github Skills (9)
pytorch10
machine-learning10
cpp10
tensorflow10
perception10
3d10
imageio9
python9
computer-graphics9
Programming languages (10)
Github contributions (5)
isl-org/Open3D
Jul 2020 - Nov 2021
Open3D: A Modern Library for 3D Data Processing
Role in this project:
ML Engineer
ML EngineerContributions:25 reviews, 16 commits, 17 PRs in 1 year 4 months
Contributions summary:Sanskar primarily contributed to integrating and testing machine learning functionalities within the Open3D library. Their work included adding a demo for the tensor API, which is crucial for numerical operations, and integrating Open3D-ML, including adding code, options, and dependency management. They also worked on image I/O functionalities and added tests.
python3d-perceptionodometrytensorflowpointcloud
MitchellTesla/Open3D-ML
Mar 2021 - May 2021
An extension of Open3D to address 3D Machine Learning tasks
Contributions:40 commits in 1 month
deep-learningaddresscomputer-visionmachine-learningopen3d
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.