Researcher (SDO-FM)

Are you interested in working with a team of visionary-doers committed to leveraging machine learning and artificial intelligence for the better of humankind?  Trillium Technologies is excited to be working with NASA on SDO-FM: A Multi-Modal Foundation Model POC for NASA’s Solar Dynamics Observatory (SDO).  We are looking for researchers and engineers with experience in generative AI, foundation models and heliophysics to join us on this journey.

How to apply: If you might be the person we are looking for and you would like to apply for the role please click the apply now button below and complete the short application form to register your interest.

About the Role

About the project 

The Solar Dynamics Observatory (SDO) is a NASA mission to understand the influence of the Sun on the Earth and near-Earth space by studying the solar atmosphere in extreme detail. SDO hosts three scientific experiments that combine to offer an unprecedented view of our closest star over a broad range of wavelengths. SDO’s combination of multiple instruments and a large temporal baseline make it an ideal candidate for a multi-modal foundation model - a new category of machine learning models trained with large-scale data so that it is generalizable for a large range of use-cases. 

An SDO Foundation Model would streamline many investigations, improve access to large datasets, and potentially unlock yet unidentified physical relationships.  The SDO Foundation Model can be a powerful tool for the Heliophysics community where the integration of AIA, HMI and EVE would create an ML-enabled Digital Twin of the Sun’s complex physical interactions. 

The project will build an end-to-end SDO Foundation Model and adaptors which will be a trailblazer example for the safe application of AI to NASA data.

The research team will follow an interdisciplinary 3-researcher structure that optimizes the collaboration between technical know-how and domain expertise (ref: FDL-X) with one machine learning (ML) expert, one heliophysics science domain expert and one foundation model expert.  The project has been segmented into three distinct stages, each capable of independent funding. The three proposed phases of this project are (Phase 1) Data collection, engineering and model choice, (Phase 2) Pre-training and validation, and (Phase 3) Fine-tuning and release.  This call for researchers is for the initial Proof of Concept (POC) for Phase 1 only. 

Join our research team

The 3-4 person research team will follow an interdisciplinary structure that optimizes the collaboration between technical know-how and domain expertise.  The team will bring a combined background in generative AI, foundation models and heliophysics expertise.   In particular we are looking for researchers who have practical experience designing, building and validating foundation models as well as cutting-edge approaches for multimodal foundation model pre-training. 

Phase 1: Timeline  February 2024 - June 2024

Responsibilities: Work part time (10-20) hrs a week to complete the following work:

  • Data Collection, Pilot task alignment and Preprocessing (8 weeks)

  • Design of Validation (2 weeks)

  • Model choice and evaluation (4 weeks)

  • Science Definition Meeting (1 week)

  Why apply

  • Engage in cutting-edge research in AI, space and heliophysics

  • This is a paid research interdisciplinary project aimed at PhD and PostDoc level

  • Work with top academic, government, and computing partners.

  • Collaborate in radical ways with top research and subject matter experts in your field

  • Work at scale with enormous compute resources

Details

Length of Contract: This will be a 5 month part-time contract (10-20) hrs a week from February to June 2024. 

Compensation: The breadth of compensation bands reflects our commitment to identifying the most suitable candidate for the role, taking into account both the time commitment you can offer and the varying levels of length and depth of experience and skills we are looking for.

Location: This is a remote position, requiring candidates to be based in the US and available during standard US business hours. 

If you are excited about pushing boundaries and interested in joining this team, please apply now.