AirStack - Open Agentic Autonomy Stack to Democratize Intelligent Robotics

Currently open to new students?

Yes
No

Description

We're working on an open source autonomy stack to democratize autonomous intelligent robotics. The goal is to make it significantly easier for anyone in the world to develop, debug, test, and deploy intelligence onto a real robot, especially mobile field robotics. We're making this stack AI and agent native to 10x productivity and lower the barrier to entry for new users.

Skills Desired

Required
  • Strong programming
  • Strong communication, collaboration, organization, and planning
  • Proactive and fast self-learner
Bonus
  • Strong software engineering principles (DRY, KISS, YAGNI, SOLID)
  • Strong software testing principles
  • Familiarity with software: ROS2, Python, C++, Linux, Bash, Git, Isaac Sim, PX4
  • Familiarity with hardware:  https://www.modalai.com/collections/drones 
  • Strong agentic coding and steering skills, i.e. knowledge how to make and track effective prompts, maintain AGENTS.md, create agent skills, model context protocol (MCP), make use of parallel agents, setup verification, etc. Important to be able to identify when the agent is WRONG and steer it in the right direction.

Student Learning Objectives

  • Learn and strengthen the skills above
  • Understand the full pipeline required to develop an intelligent robot from start to finish
  • Contribute towards AirStack paper publication
  • Support autonomy for all lab projects using AirStack

Classes Accepted into Project

Junior
Senior
Graduate Student
Not a hard limit. We care more about talent and potential.

Compensation

Units 9
Units 12
Pay

Contact