Machine Learning Researcher, Climate

Machine Learning Researcher, Physics & Weather Modeling San Francisco, CA | 5 days on-site Our client is a research-stage AI company focused on building intelligence systems that can predict future outcomes and recommend optimal actions across complex physical domains. About the Role You will design, train, and evaluate large-scale foundation models grounded in physics, using weather as a primary training environment. This role spans the full ML stack, from petabyte-scale data pipelines and distributed training to novel model architectures and rigorous ablation studies. You’ll work closely with a small, senior research team in San Francisco, fully on-site, to push the frontier of causal modeling in real-world physical systems. Responsibilities Work across the end-to-end ML stack, including data ingestion, modeling, evaluation, and training infrastructure. Implement and iterate on novel model architectures and training algorithms for large-scale physics and weather models. Build and optimize data pipelines and training infrastructure for petabyte-scale, multimodal datasets. Design, run, and analyze experiments and ablations to understand model behavior and drive performance gains. Stay current with cutting‑edge ML research and bring relevant ideas into the modeling and training roadmap. Collaborate with a small team of researchers and engineers to ship high‑impact models into internal and external use cases. Qualifications Strong grasp of machine learning fundamentals and depth in at least one domain such as computer vision, sensor fusion, language models, or physics‑informed neural networks. Hands‑on experience training large‑scale models and interpreting experiment results through careful analysis and ablation studies. Proven experience building and optimizing massive data pipelines, ideally at petabyte scale. Familiarity with distributed training and inference on large GPU clusters. 1+ years of experience training large‑scale foundation models from scratch in industry or research settings. Proficiency in Python and modern deep learning frameworks such as PyTorch, plus experience with common experiment‑tracking tools. Ability and willingness to work in‑person five days per week in the San Francisco metro area. Preferred Skills Background in meteorology, computational fluid dynamics, and/or numerical simulation of physical systems. Experience with multimodal datasets and sensor fusion across spatial‑temporal data. Prior work on physics‑based or weather‑related modeling problems. Experience at frontier ML, robotics, or autonomy organizations, or early‑stage deep‑tech startups. Pay range and compensation package Competitive compensation package commensurate with experience. Comprehensive health, dental, and vision coverage. Equity participation in an early‑stage, high‑upside AI company. #J-18808-Ljbffr RecruitSeq