Ratnesh Madaan
ML Engineer at Gather AI
San Francisco, California, United States
Summary
🤩
Rockstar🎓
Top SchoolRatnesh Madaan is an ML Engineer based in San Francisco with 11 years of experience bridging robotics research and production-grade autonomous systems. He was the first hire in Microsoft’s Autonomous Systems and Robotics Research group, contributing to research-to-deployment projects and improving developer tooling such as AirSim Docker environments. His background includes an MS in Robotics from Carnegie Mellon where he developed perception and planning algorithms for UAVs, published IROS work on wire detection, and built synthetic datasets and embedded deployments on NVIDIA TX2. Ratnesh blends deep algorithmic work (computer vision, planning) with practical systems skills (Docker, SLURM, ROS, embedded inference), enabling smooth transitions from prototypes to scalable experiments. Currently at Gather AI, he focuses on making autonomous aerial systems robust in real-world conditions. Colleagues note his knack for turning hard research problems into repeatable engineering pipelines and reproducible toolchains.
11 years of coding experience
7 years of employment as a software developer
Indian Institute of Technology RoorkeeM.S. in Robotics Robotics, M.S. in Robotics Robotics at Carnegie Mellon University
Github Skills (9)
script10
docker10
bash10
dockers10
cicd10
containerization9
ubuntu9
automations8
automation8
Programming languages (7)
Github contributions (5)
microsoft/AirSim
Nov 2018 - Sep 2020
Open source simulator for autonomous vehicles built on Unreal Engine / Unity, from Microsoft AI & Research
Role in this project:
DevOps Engineer
DevOps EngineerContributions:3 releases, 2 reviews, 199 commits in 1 year 10 months
Contributions summary:Ratnesh primarily focused on improving the AirSim's Docker environment. Their contributions included creating Dockerfiles, build scripts, and run scripts, enabling the building and execution of the AirSim simulator within Docker containers. These changes included creating images for both windowed and headless runs, and also integrated a python script to build the docker image. The user also updated the existing Docker build scripts for efficiency.
deep-reinforcement-learningsimulationsimulatorunitysimulator-source
madratman/research_resources
Mar 2016 - Sep 2017
Contributions:48 commits, 3 pushes in 1 year 6 months
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.