Machine Learning Engineer

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.

Mariana Minerals is building the critical minerals supply chain from the ground up—and we're looking for Machine Learning Engineers 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 Machine Learning Engineer at Mariana, you'll help build and improve the machine learning systems that control our mineral refining facilities. You'll start with well-scoped problems inside our simulators and training pipelines—and ramp quickly toward owning models that run on real, operating plants. Your work won't live behind dashboards or proxy metrics; you'll see its impact in real recovery rates, energy consumption, reagent usage, and uptime.

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.

• →

  Run reinforcement learning experiments in our physically realistic simulators of mineral processing operations, and help turn the results into better controllers.

• →

  Build and refine pieces of our training environments—reward functions, observations, and action logic—with guidance from senior engineers.

• →

  Train control models, track and interpret their performance, and dig into why a model underperforms.

• →

  Help close the gap between simulation and reality by comparing model behavior against real plant data and flagging where the physics diverges.

• →

  Write clean, well-tested code and contribute to the services that put models into production.

• →

  Partner with process and chemistry experts to understand the unit operations you're modeling.

   

• 2-8+ years of experience (including internships or research) in machine learning, reinforcement learning, or scientific computing—or a strong recent graduate with demonstrated project depth.

• Solid grounding in machine learning fundamentals, with working knowledge of modern deep learning; exposure to reinforcement learning is a strong plus.

• Proficiency in Python and comfort reading and debugging an existing codebase.

• Curiosity about physical, industrial systems and eagerness to learn chemistry and process engineering from experts who will challenge your assumptions.

• A self-starter who asks good questions, ships, and escalates blockers early.

   

We own the projects, generate the data, and close the loop. Every facility we build makes the software smarter—and the next facility faster and cheaper.

Mining is one of the last major industrial sectors that hasn't been rebuilt with modern software. The opportunity here isn't a feature gap—it's entire workflows and systems that don't exist yet.

Your work will directly shape how critical minerals are produced at scale in the coming decades.