Andrew Szot
Research Intern at Apple
United States
Summary
🤩
Rockstar🎓
Top SchoolAndrew Szot is a Ph.D. student in Machine Learning at Georgia Tech and a research-focused software engineer with 11 years of experience building robotics and embodied-AI systems at top labs and tech companies including Apple, Meta, and Facebook AI. He blends deep research instincts with practical engineering, contributing back-end and motion-planning improvements to the popular Habitat-Lab framework—refactoring rendering pipelines and adding an OpenAI Gym wrapper to make robot interaction workflows more robust and accessible. His internships span industry and academia, from USC’s CLVR and MCL labs to production-facing roles at Airbnb and eBay, reflecting a knack for translating research prototypes into deployable tools. Known for debugging tricky interactive-play and sensor-visualization issues, he brings careful systems thinking to complex perception and control stacks.
11 years of coding experience
4 years of employment as a software developer
Bachelor of Science (BS) Mathematics (Minor) Computer Science, Bachelor of Science (BS) Mathematics (Minor) Computer Science at University of Southern CaliforniaDoctor of Philosophy - PhD Machine Learning, Doctor of Philosophy - PhD Machine Learning at Georgia Institute of TechnologyInglemoor High School
English
Github Skills (10)
machine-learning10
robotics10
python10
reinforcement-learning10
deep-reinforcement-learning9
computer-vision9
deep-learning8
deeplearning-ai8
ai8
simulator8
Programming languages (7)
Github contributions (5)
facebookresearch/habitat-lab
Jun 2021 - Jan 2023
A modular high-level library to train embodied AI agents across a variety of tasks and environments.
Role in this project:
Back-end Developer & Robotics Engineer
Back-end Developer & Robotics EngineerContributions:453 reviews, 51 commits, 146 PRs in 1 year 7 months
Contributions summary:Andrew primarily focused on debugging and enhancing the interactive play script, a core component for robot control and environment interaction within the Habitat-Lab framework. They also contributed to implementing motion planning capabilities, including the addition of an OpenAI Gym wrapper. Key improvements involved refactoring the observation-to-image functionality for better rendering and automatic sensor display. Additionally, they worked on a bug fix which updated the installation path in colab scripts.
ai-agentaicomputer-visionroboticssimulator
ASzot/PersonalWebsite
Jan 2017 - May 2020
Contributions:134 pushes, 1 branch, 2 issues in 3 years 4 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.