The Role
Constellation is seeking an ambitious Graduate or PhD Research Intern to join our Data Science / AI team. You will research and develop cutting-edge machine learning models to solve complex aerospace challenges, from predictive maintenance to autonomous orbital navigation.
Responsibilities
Conduct independent research to design and train novel machine learning architectures.
Analyze massive datasets derived from flight telemetry and satellite sensors.
Prototyping and testing algorithms in simulated aerospace environments.
Publish internal papers and present findings to the core engineering team.
Requirements
Currently pursuing a Master's or Ph.D. in Computer Science, Aerospace Engineering, Mathematics, or a related field.
Strong theoretical understanding of deep learning, computer vision, or reinforcement learning.
Proficiency in Python and standard ML frameworks (PyTorch, TensorFlow, or JAX).
Ability to work on-site in Seattle for the duration of the internship.
Skills Required
- Currently enrolled in an MS or PhD program (CS, EE, Aerospace, Applied Math, or related)
- U.S. person (citizen, green card holder, or asylee/refugee) due to ITAR-controlled data access
- Strong low-level engineering skills and comfort with scientific/ML tooling (C++, Python, Rust)
- Ability to own projects end-to-end: scoping, implementation, testing, and communication
- Clear written and verbal communication and strong collaboration habits
- Experience with APIs, cloud infrastructure, or data-intensive systems
- Familiarity with model evaluation, experiment tracking, and reproducibility
- Background in networking, geospatial systems, telecom, or space-tech
What We Do
Constellation Space builds ConstellationOS, an AI-native operating system that forecasts satellite link degradation minutes ahead and autonomously reroutes traffic under policy to prevent data loss. The platform ingests telemetry, uses physics-informed ML to predict failures with high accuracy, and executes rapid, policy-bound reroutes to provide mission assurance and scalable orchestration for large satellite constellations.
