Software Engineer

About the role

Muon Space is expanding its High Performance Compute (HPC) team to accelerate mission-critical data products and unlock a growing pipeline of computer-vision and ML workloads across ground and flight systems.

This role works directly with the team that produces our image data products. You'll design and implement the image processing algorithms and models that power Muon's ground and flight products, including segmentation, feature classification, labeling, traditional image computation, and related tasks, with a strong emphasis on low latency and deployability onto cloud data centers and the edge. You'll also own the processing and ML data engineering foundation.

This position is hybrid and requires working on-site in our San Jose, CA office three days per week.

Responsibilities

• Design, train, evaluate, and iterate on image processing models for Muon's ground processing and onboard flight systems.
• Build and own the image and ML data engineering foundation.
• Optimize algorithms and models for low latency operation on cloud compute environments, and edge/onboard deployment in constraint environments.
• Contribute to high-performance reference algorithms and implementations and benchmark them.
• Hand algorithms and models off into the cloud serving stack and partner with mission and payload teams to define requirement needs and acceptance criteria.
• Own verification and validation, including unit, integration, and performance regression tests.

Required Qualifications

• Bachelor's or Master's degree in Computer Science, Computer Engineering, Electrical Engineering, Applied Math, or a related technical field.
• 3+ years of professional experience developing ,shipping, and operating image computation or ML systems.
• Strong PyTorch skills, including designing, training, and evaluating models end-to-end.
• Demonstrated production experience with low-latency image computation models, deployed as containerized workloads on cloud infrastructure (AWS preferred).
• Hands-on ML data engineering: dataset curation, labeling, and versioning for training and evaluation. Measuring and improving algorithmic quality and performance.
• Strong Python skills beyond notebooks: tested, packaged, code-reviewed code that runs unattended in production.
• Strong written and verbal communication and ability to lead and conclude cross-functional technical discussions.
• Ability and willingness to obtain and maintain a U.S. security clearance. Active clearance is a plus.