AI/ML Scientist, Planetary Science

Relativity Space•Long Beach, CA

1d•$115,000 - $158,500•Hybrid

About The Position

Relativity Space is seeking an AI/ML Scientist to develop and deploy machine learning systems for their 2028 Mars orbital mission. This role involves working at the intersection of AI and planetary science, addressing challenges with sparse data, heterogeneous instruments, and dynamic planetary systems. The scientist will build AI models to run on spacecraft, focusing on enhancing Mars atmospheric modeling and weather forecasting, and developing methods for multi-modal data fusion to reconstruct 3D representations from various datasets. Additionally, the role includes building systems for autonomous in situ science, enabling real-time analysis of observations, detection of significant events, and autonomous re-tasking of the spacecraft. This is an applied research role requiring end-to-end problem ownership, collaboration with scientists and engineers, and the application of machine learning principles to amplify science discovery. The position is a collaboration between Relativity's Interplanetary Sciences Program and Polymathic AI, with potential travel to New York.

Requirements

PhD in machine learning, computer science, physics, or a related technical field
Demonstrated experience with transfer learning, domain adaptation or model fine-tuning, particularly in low-data or out-of-distribution settings
Experience with applying machine learning in physical datasets
Working knowledge of multi-modal data fusion
Ability to own problems end-to-end: from dataset understanding through model development, evaluation, and deployment
Excited to collaborate with a diverse group of scientists and engineers, and further planetary science

Responsibilities

Develop and deploy machine learning systems for the 2028 Mars orbital mission.
Enhance Mars atmospheric modeling and weather forecasting using Machine Learning techniques.
Create a weather forecasting model to be run on the spacecraft at Mars, integrating Earth-derived datasets and Martian atmospheric physics.
Optimize weather forecasting models for spacecraft deployment.
Develop and build methods for multi-modal data fusion to integrate complementary datasets (2D images, 3D models, geologic maps, radar soundings) for coherent 3D representations.
Build systems for autonomous in situ science, including real-time observation analysis and detection of scientifically significant events.
Develop AI decision-making layers for autonomous spacecraft re-tasking based on onboard inference.
Drive problem framing, build and evaluate systems end-to-end.
Communicate results clearly to scientists and engineers.
Combine core principles of machine learning with deep learning tools to amplify science discovery.