Senior Machine Learning Scientist, Climate & Hydrology

Flagship Pioneering•Cambridge, MA

4d•Hybrid

About The Position

Flagship Pioneering is seeking a Senior Machine Learning Scientist, Climate and Hydrology to lead the scientific direction and machine learning development for hydrology-aware climate modeling within their broader environmental modeling platform. This role is at the intersection of hydrology, weather and climate science, and large-scale machine learning. The Sr. Scientist will help shape how hydrologic process understanding, climate data, and modern ML methods are brought together in next-generation prediction systems, with emphasis on scientifically grounded model development and evaluation. The individual will work across science, ML, engineering, and data teams to define research priorities, guide model training and benchmarking, build reproducible workflows, and translate scientific insight into scalable model development. This is a cross-functional role requiring strong technical depth, structured scientific thinking, and the ability to move between foundational research and applied execution.

Requirements

PhD in machine learning, computational science, Earth science, atmospheric science, hydrology, AI, computer science, or a related quantitative discipline.
5+ years of postdoctoral, industry, or applied research experience in climate ML, weather ML, hydrologic modeling, Earth system modeling, or a closely related field.
Demonstrated experience with ML-accelerated weather, climate, or hydrology models, with a strong publication track record in the area.
Experience working with large climate datasets, including reanalysis products, remote sensing datasets, observational datasets, and model output.
Experience with the computational infrastructure required to manage, preprocess, and train on large-scale climate datasets, preferably in the AWS ecosystem.
Strong programming skills in Python and experience with modern ML frameworks such as PyTorch.
Ability to design rigorous evaluation frameworks, performance metrics, and benchmarking approaches for environmental prediction systems.
Strong technical writing and communication skills, including reports, presentations, and peer-reviewed publications.
Demonstrated ability to work independently in fast-paced, ambiguous environments while collaborating effectively across disciplines.

Nice To Haves

Background in scientific ML, spatiotemporal modeling, data assimilation, hybrid physics-ML methods, or related approaches is strongly preferred.
Experience leading cross-functional scientific efforts, mentoring researchers, or helping define research roadmaps is preferred.

Responsibilities

Lead scientific and technical efforts at the intersection of hydrology, climate science, and machine learning.
Help define research priorities, modeling directions, and evaluation strategies for next-generation climate and environmental prediction systems.
Contribute to the development and improvement of ML-based modeling approaches informed by physical and Earth system science.
Work with large-scale climate, weather, hydrology, and remote sensing datasets to support model development and scientific analysis.
Build and oversee reproducible workflows for data processing, model training, benchmarking, and validation.
Collaborate closely with research, engineering, and data teams to translate scientific goals into scalable technical execution.
Guide assessment of model performance, uncertainty, and scientific robustness across a range of environmental conditions and applications.
Communicate findings through internal reviews, external collaborations, publications, and technical presentations.
Help shape the broader scientific roadmap and contribute to team growth and cross-functional leadership.