Relativity Space

AI/ML Scientist, Planetary Science

Relativity Space$115K — $158K *
Aerospace & Defense
Less than 5 years of experience
Job Overview by Ladders

Qualifications

  • PhD in machine learning, computer science, physics, or related field
  • Experience in transfer learning, domain adaptation, or model fine-tuning in low-data or out-of-distribution settings
  • Application of machine learning techniques on physical datasets
  • Knowledge of multi-modal data fusion
  • Ability to manage problems from dataset understanding to model deployment
  • Collaborative mindset to work with diverse scientists and engineers

Responsibilities

  • Develop and deploy AI models for Mars atmospheric modeling and weather forecasting
  • Integrate Earth-derived datasets with Martian atmospheric physics using machine learning techniques
  • Create methods for 3D data reconstruction from heterogeneous datasets
  • Monitor and analyze real-time data on spacecraft for scientific events
  • Design AI decision-making systems that autonomously re-task spacecraft based on in-flight data analysis
  • Drive end-to-end problem framing and system evaluation in a research-driven environment
  • Communicate findings effectively to interdisciplinary teams

Benefits

  • Competitive salary and equity
  • Generous PTO and sick leave policy
  • Parental leave
  • Annual learning and development stipend
  • Opportunity for travel to partner institutions and mission integration sites
Full Job Description
We are seeking an AI/ML Scientist to develop and deploy machine learning systems that unlock new science from our 2028 Mars orbital mission. This is a rare opportunity to work at the intersection of frontier AI methods and planetary science - building new approaches for a data environment with disparate datasets and often sparse observations, heterogeneous instrument modalities, and a dynamic planetary system we are only beginning to understand. The problems will be diverse and the solutions open-ended. You will be building AI models to run on the spacecraft in Mars orbit. This position is jointly advised by Relativity's Interplanetary Sciences Program and Polymathic AI, a research collaboration initiative pioneering foundation models for scientific data across physical disciplines.

One topic is enhancing Mars atmospheric modeling and doing weather forecasting. The historical record of Mars weather is fragmentary. You will develop and apply Machine Learning techniques to combine Earth-derived atmospheric datasets and known Martian atmospheric physics to create a weather forecasting model to be run on the spacecraft at Mars with real-time collected data as the input. This development includes optimizing the weather forecasting model to run on the spacecraft at Mars.

Another challenge is multi-modal data fusion. You will develop and build methods that reconstruct coherent 3D representations by integrating complementary datasets of 2D surface images, 3D surface models, geologic mapping of units, and radar depth soundings, each having different geometry, resolution, temporal cadence and past and new data.

These approaches will then be applied to autonomous in situ science. You will build systems that monitor observations, analyze them in real-time on the spacecraft and detect scientifically significant events based on known phenomenology of Mars as well as novelty detection. Critically, you will develop the AI decision-making layer that closes the loop, autonomously re-tasking the spacecraft to acquire follow-up observations from onboard inference on flight hardware. This capability is central to the mission architecture and represents one of the most ambitious applications of autonomous science in any planetary mission to date.

This is a high-ownership, applied research role on a lean team. You will drive your own problem framing, build and evaluate systems end-to-end, and communicate results clearly to scientists and engineers alike. Fulfilling this objective requires creativity to combine core-principles of machine learning to the practical tools of deep learning with a laser focused goal to amplifying the science discovery of the Mars mission.

The selected candidate will work in close collaboration with Interplanetary Sciences Team at Relativity headed by Dr. Margarita Marinova and Polymathic AI headed by Prof. Shirley Ho at Simons Foundation and New York University. The collaboration requires some travel to New York.

The selected candidates will join a vibrant, interdisciplinary team based in Long Beach, CA and New York City, spanning NYU and the Flatiron Institute, composed of rocket scientists, machine learning researchers, engineers, and other domain scientists. This collaborative environment at Relativity and Polymathic AI offers a unique opportunity to work on cutting edge AI models and advance AI for planetary discovery.

About You
  • 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

This position may require occasional travel to partner institutions, test facilities, and mission integration sites (
At Relativity Space, we are committed to transparency and fairness in our compensation practices. Actual compensation will be determined based on experience, qualifications, and other job-related factors.

Compensation is only one part of our total rewards package. Relativity Space offers competitive salary and equity, a generous PTO and sick leave policy, parental leave, an annual learning and development stipend, and more! To see some of the benefits & perks we offer, please visit here.

Hiring Range:

$115,000-$158,500 USD

About Relativity Space

Relativity Space is an American aerospace manufacturer that is developing 3D printed rockets. The company was founded in 2015 by Tim Ellis and Jordan Noone, and is headquartered in Los Angeles, California. Relativity Space's goal is to reduce the cost and time required to produce rockets by using 3D printing technology. The company's rockets are designed to be fully reusable, which could significantly reduce the cost of space launches. Relativity Space has received funding from a number of investors, including Mark Cuban and Playground Global.
Learn more about Relativity Space
Size
200 employees
Industry
Founded
2016

Similar Jobs

More Jobs at Relativity Space

More Aerospace & Defense Jobs

Find similar AI/ML Scientist, Planetary Science jobs: