Intern - Machine Learning

What we need

We want to learn from you! Our teams at Symbotic value the early career talent that helps us solve critical issues in creative and innovative ways. That is why we offer Internship and Co-op programs where students have the opportunity to work alongside industry professionals on some of our most pivotal projects. We invite students from institutions across the country to apply online or engage with our teams on campus at career fairs and other events. Symbotic offers an extensive calendar of events including Lunch and Learns, Social Outings, and Volunteer opportunities for our Interns and Co-ops to engage in.  

The Summer Intern session is a 12-week, full-time (40 hours Monday-Friday) program while the Co-op cohorts typically run 16-weeks in the Spring and Fall. In both programs, students are paid a competitive hourly rate. Continue reading to learn more about this exciting opportunity! 

What you’ll do

• Derive and obtain machine-learnable data by collecting, cleaning, preprocessing, and labeling data generated by our robotic systems and maintenance records.  

• Work with site operators to track and understand robot maintenance issues.  

• Establish pipelines that train, deploy and maintain ML models in the cloud using Microsoft Azure.  

• Evaluate and implement cutting-edge ML tools, platforms, and services.   

• Create visualizations to extract understanding from spatial- and time-domain data.  

• Develop high quality code and packages following software engineering best practices.

What you’ll need

• Currently pursuing degree in a technical field (Mathematics, Physics, Engineering or Computer Science). Graduate students preferred.  

• Strong programming skills in Python and familiarity with SQL is required. 

• Rigorous analytical and critical thinking. Demonstrated ability to apply the scientific method to novel problems in the hardware engineering domains. 

• Excellent communications skills, including the ability to work collaboratively with cross-functional teams. 

• ML frameworks such as scikit-learn, TensorFlow, or similar procedures and tooling supporting rigorous and repeatable scientific computing, including data management and experiment tracking is expected. 

• Experience with source control (git or similar), software testing frameworks (pytest or similar), and CI/CD pipelines (Jenkins or similar)  

• Enjoys learning new technologies, skills, and techniques as well as teaching them to others. 

• Familiarity with cloud-hosted environments (AWS, GCP, Azure) and containerization technologies (Kubernetes, Docker, etc.) is a strong plus.