Intern- Machine Learning Ops

Exol•Wilmington, MA

1d•$32 - $42•Onsite

About The Position

Symbotic is seeking an Intern- Machine Learning Ops to join our ML Operations team within our Software organization. This role will focus on building, scaling, and deploying machine learning systems to enhance the health, reliability, and performance of the company's autonomous robot fleet. The internship is for the Summer term (May-Aug). Early career talent at Symbotic contributes to real projects, collaborates with experienced professionals, and gains hands-on exposure to cutting-edge technologies in warehouse automation. Interns receive mentorship, professional development, networking opportunities, and a structured event calendar to foster community and career growth. Symbotic also provides transportation and housing benefits for eligible students.

Requirements

Pursuing PhD or Master's Degree in related field
Coursework or project experience in computer science, software engineering, robotics engineering, machine learning, or a related technical discipline.
Proficiency in Python or C++ and the ability to deliver high-quality, working code.
Experience with cloud-based infrastructure or services, including Google Cloud Platform (GCP) or Microsoft Azure.
Experience working with complex data systems, including data storage, telemetry, camera, or sensor data.
Familiarity with machine learning deployment technologies such as ONNX, TensorRT, Docker, or edge computing platforms.
Strong collaboration and problem-solving skills for work across machine learning, software, hardware, perception, and operations teams.

Responsibilities

Architect and scale software platforms that support current and future autonomous capabilities.
Collaborate with machine learning research and development teams to ensure new models meet production deployment requirements.
Optimize robotic fleet deployment pipelines from merge requests through testing and rollout using ONNX, TensorRT, and custom hardware.
Maintain and improve edge computing infrastructure to support real-time performance and reliability.
Build machine learning pipelines for dataset curation, labeling, training, validation, and evaluation metrics.
Develop simulation, diagnostics, monitoring, and alerting capabilities that accelerate robotic system evaluation and reduce mechanical maintenance during fleet scale-up.
Improve robotic software, compilation architectures, and Docker Compose configurations to increase machine learning performance and balance shared hardware resources.