SWE Intern, AI, Navigation & Controls (Undergraduate)
Are you passionate about advancing the capabilities of autonomous robots through cutting-edge AI and machine learning? Do you enjoy working on innovative solutions that bring state-of-the-art research into real-world applications? Our growing robotics startup is looking for a SWE Intern, AI, Navigation, and Controls, to join our team. Your contributions will help define how robots operate in dynamic, real-world environments, bringing meaningful impact to customers and industries.
In this role, you will develop and maintain software for our on-robot autonomy stack, applying the latest advancements in AI research, including navigation, controls, multimodal models, and large language models (LLMs). You’ll work on tasks such as training machine learning models for navigation, optimizing them for on-robot deployment, and using machine learning and AI to improve fleet-level performance.
Collaborative Robotics is a team of innovators and builders redefining the future of human-robot interaction. We are working to realize a world where robots are a trusted extension of your surroundings. They work, adapt, and react around you. Not the other way around.
This role is located at our Santa Clara, CA headquarters.
This is a full time, 3-month (12-week) internship running June–August 2026.
The application deadline for this role is January 11th, 2026. Interviews will take place mid-late January 2026.
Key Responsibilities:
Develop and maintain software for our on-robot autonomy stack leveraging the latest AI research in navigation, controls, multimodal models, end-to-end models, and LLMs
Leverage open source models and the latest research papers to improve the capabilities of our robots operating in customer sites
Train machine learning models for navigation, controls, and behaviors on our robot
Optimize trained models for on-robot deployment
Minimum Qualifications:
Pursuing an undergraduate degree in Computer Science, Robotics, AI, Machine Learning, or related field.
Experience with deep learning frameworks such as Pytorch, Tensorflow, etc.
Understanding of multimodal models, modern ML architectures and approaches (transformers, diffusion models, reinforcement learning, etc.)
Proficiency with Git, version control, and Linux environments.
Skilled in Python
Highly motivated teammate with excellent oral and written communication skills.
Enjoy working in a fast paced, collaborative and dynamic start-up environment as part of a small team.
Willing to occasionally travel.
Must have and maintain US work authorization.
Preferred Qualifications:
Demonstrated ability to deploy ML models to robots in production.
Experience with end to end learning approaches for navigation and controls
Experience with perception for robotics, autonomous vehicles, or other real world applications.
Practical experience with ML software engineering best practices – for example, experiment tooling, data pipelines, model training, and workflow automation.
Experience optimizing ML models for deployment in compute constrained environments.
Familiarity with edge compute architectures.
The non-exempt hourly range for this intern position is $30-$35/hr. Our ranges are determined by role and experience level. The range reflects the minimum and maximum target for intern rates for the position in Santa Clara, CA. Within the range, individual pay is determined by additional factors, including job-related skills, experience, and relevant education or training.
Cobot is an Equal Opportunity Employer. All qualified applicants will receive consideration for employment without regard to legally protected characteristics. We are committed to providing reasonable accommodations for candidates with disabilities in our recruiting process. If you need any assistance or accommodations due to a disability, please let your recruiter know.
To all recruitment agencies: Collaborative Robotics does not accept agency resumes. Please do not forward resumes to our employees. Collaborative Robotics is not responsible for any fees related to unsolicited resumes.