Staff Machine Learning Engineer

ABOUT MARIANA MINERALS Mariana Minerals is a software-first, vertically integrated minerals company on a mission to supply the critical minerals powering modern energy, AI, and defense technologies. We’re reimagining the minerals supply chain by combining deep industry expertise with advanced software, automation, and data-driven decision-making. THE ROLE Mariana Minerals is building the critical minerals supply chain from the ground up—and we're looking for a Staff Machine Learning Engineer to help make it autonomous. We're not a software company selling tools to mining operators. We are a mining company that builds software. Mariana designs, builds, commissions, and operates our own mines and refineries. We develop proprietary chemical processes and run them at lab, pilot, and commercial scale. Today, we're producing battery-grade lithium salts from real oil and gas wastewater in our facilities. Our first commercial-scale lithium production facility, Lithium One, is targeting initial production in Q1 of 2027. As a Staff Machine Learning Engineer at Mariana, you'll set the technical direction for how we make refining autonomous. You'll define how control models are built, validated, and trusted on live equipment across our circuits and facilities—and you'll personally take on the hardest modeling problems standing between us and fully autonomous operations. Your decisions will show up in real recovery rates, energy consumption, reagent usage, and uptime across every plant we run. THE TECH This is some of the most interesting applied AI work happening today. Our internal platform, uses the same reinforcement learning toolkits that power self-driving vehicles and humanoid robots—but applied to autonomous, short-interval control of mineral refining circuits. Models adjust operating set points and configurations in real time, optimizing across lithium recovery, reagent consumption, energy intensity, and equipment uptime simultaneously. The environment is noisy and non-stationary: wastewater compositions shift, ore grades change, equipment ages. The system must continuously adapt. The end goal is fully autonomous refining operations. When you ship here, you can literally watch the physics change. Under the hood, that means training control models inside physically realistic simulators of our process units, then closing the gap against real plant data before anything touches live equipment. WHAT YOU’LL DO - Own the autonomy roadmap across multiple circuits and facilities—deciding which unit operations to automate next and where investment in simulation and modeling pays off. - Define how control models are validated and certified safe to deploy on real refining equipment, including how the gap between simulation and reality is measured and closed. - Set the standards for our simulators and our modeling stack, so the whole team builds controllers that are reproducible, safe, and grounded in real project economics. - Personally solve the hardest modeling and control problems—non-stationarity, safety constraints, and multi-objective optimization across recovery, reagent use, energy, and uptime. - Partner with leadership on major capital and operational decisions, translating techno-economic and process insight into strategy. - Multiply the team through technical direction, design review, and mentoring of engineers at every level—and partner with our data engineering leaders to shape the data platform the autonomy roadmap requires. You own the modeling and the on-plant outcome; they own the backbone. DESIRED QUALIFICATIONS - 8+ years in machine learning engineering (or an exceptional 6+ with demonstrated org-level technical leadership), including production ML or control systems that ran in the real world. - A track record of setting technical direction for ML systems in physical, industrial, robotics, or control domains. - Deep expertise in reinforcement learning under non-stationarity, simulation and digital twins, and closing sim-to