AI/ML Lead

AI / ML Lead We're looking for an AI / ML Lead to join us at Atomionics to build a new ML team in our San Francisco office, where they will spearhead our efforts to build a comprehensive model of natural resources throughout the world. The world needs 500% more metal over the next 10 years. These are metals like copper, cobalt, nickel, and lithium, which form the bedrock of the infrastructure that needs to be built. But drilling for these metals fails 89% of the time. We are building a large planet model to solve this, powered by our proprietary quantum gravimetry technology that can collect 10,000x better gravity data than other sensors. ML, AI – and you – will be critical to this effort. Atomionics is backed by BHP Ventures, In-Q-Tel, among other investors. Projects you'll lead: Developing an agentic geologist that can understand text and map data to model the planet's geology Building models that can predict where precious minerals lie beneath the Earth's surface Building simulations of the Earth's geological history Extending classical gravity inversion models to be multimodal An ideal candidate will not just overcome challenges along the way but also thrive in the ambiguity of the space. They will be hands-on when appropriate as they lead the team to build new models, define North Star metrics, and design loss functions. They will not just know how to train new ML models on terabytes of unstructured data – but also know when it's appropriate to apply statistical models that can learn from scarce data. Requirements: Broad exposure to ML, including classical methods, Bayesian learning, deep learning, LLMs; with deep experience in deep learning / LLMs 3+ years of experience managing a team of 5 or more ML engineers with capacity to manage more At least 10 years of experience applying machine learning in an industry or academic setting, including experience building new models from the ground up MS or PhD (preferred) in a quantitative area such as computer science, statistics, physics, or electrical engineering Experience defining new metrics in ambiguous or new spaces Basic familiarity with classical statistics (p-values, confidence intervals, etc.) Great communication: an ability to mentor ML engineers or graduate students, to communicate across organizations, and to share results publicly Nice to have: Deep familiarity with physics, classical statistics, and/or geospatial modeling Public examples of your work (publications in top ML or statistics journals or conference proceedings) Experience with information retrieval and/or fine-tuning large language models Experience with computational modeling in fields such as simulation, finite element analysis, differential equations, or related methods Atomionics