Mitchell Spryn
Research Engineer at Helm.ai
Seattle, Washington, United States
Summary
🤩
Rockstar🎓
Top SchoolMitchell Spryn is a research engineer with nine years of experience building and deploying large-scale deep learning systems for autonomous vehicles and AR/VR applications. He currently develops generative-AI-driven path planning and intent prediction models at Helm.ai and has a track record of scaling ML training infrastructure to petabyte datasets from prior roles at Motional and Microsoft. His work bridges research and production—contributing to open-source projects like the Microsoft Autonomous Driving Cookbook and integrating AirSim for distributed reinforcement learning experiments. Comfortable across model development, deployment, and large-scale data pipelines, he pairs hands-on algorithmic contributions (reward functions, model updates) with systems engineering to make research reproducible and debuggable. Based in Seattle, he brings an uncommon mix of autonomy, AR research, and big-data engineering grounded in EE and physics fundamentals.
9 years of coding experience
12 years of employment as a software developer
The University of Alabama
Github Skills (10)
keras10
machine-learning10
distributed-training10
deep-learning10
tensorflow10
python10
autonomous-driving10
reinforcement-learning10
airsim10
jupyter-notebook9
Programming languages (5)
Github contributions (5)
microsoft/AutonomousDrivingCookbook
Dec 2017 - Mar 2018
Scenarios, tutorials and demos for Autonomous Driving
Role in this project:
ML Engineer
ML EngineerContributions:15 commits, 4 PRs, 16 pushes in 3 months
Contributions summary:Mitchell's contributions center on the development and modification of distributed reinforcement learning algorithms within the context of autonomous driving. Their work includes integrating AirSim, a simulation platform, for model training and testing. The user implemented and modified core components like the reward function and model updates, crucial for the learning process. They also introduced local run functionality for easier debugging.
airsimroboticsautonomousdeep-learningautonomous-driving
mitchellspryn/UrdfSim
Jan 2019 - Mar 2021
Contributions:1 release, 18 commits, 2 PRs in 2 years 2 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.