Mariana Minerals is building the critical minerals supply chain from the ground up, and the team is focused on making mineral refining autonomous. This role gives you hands-on ownership of machine learning systems that control real refining facilities, starting in physically realistic simulators and moving toward models that run on operating plants. You’ll work on reinforcement learning for autonomous, short-interval control, with direct impact on recovery, energy, reagent usage, and uptime.

Location: San Francisco, CA (onsite)
Compensation Range: USD 120,000 - 180,000 per yearly
Minimum Experience: 2 years

What you’ll work on

You’ll run reinforcement learning experiments inside physically realistic simulators of mineral processing operations, then help turn results into better controllers. The goal is to bridge simulation and reality by comparing model behavior against real plant data and identifying where the physics diverges, so training can translate to safer, more reliable real-world control.

Run reinforcement learning experiments in internal, physically realistic simulators and iterate toward improved controllers.
Build and refine training environment components, including reward functions, observations, and action logic, with guidance from senior engineers.
Train control models, track and interpret performance, and investigate why a model underperforms.
Close the simulation-to-reality gap by comparing against real plant data and flagging physics mismatches.
Write clean, well-tested code and contribute to services that put models into production.
Partner with process and chemistry experts to understand the unit operations you model.

Core technologies

Python
Reinforcement learning
Deep learning

What we’re looking for

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; reinforcement learning exposure is a strong plus.
Proficiency in Python and comfort reading and debugging an existing codebase.
Curiosity about physical, industrial systems, plus eagerness to learn chemistry and process engineering from experts who challenge assumptions.
A self-starter mindset: asks good questions, ships, and escalates blockers early.

How the work is different

Mariana Minerals uses reinforcement learning toolkits commonly associated with self-driving vehicles and humanoid robots, adapted for autonomous, short-interval control of mineral refining circuits. Models adjust operating set points and configurations in real time, optimizing simultaneously across lithium recovery, reagent consumption, energy intensity, and equipment uptime.

The environment is noisy and non-stationary: wastewater compositions change, ore grades vary, and equipment ages. Training control models in physically realistic simulators is only the start; the work includes closing the gap against real plant data before models touch live equipment.

Compensation

$120K - $180K

How we work (culture)

Extreme Ownership – take full responsibility for outcomes and drive toward solutions.
Engineer Out Requirements, then Automate – simplify, optimize, and automate for scale.
Share Your Legos – collaborate openly, share knowledge, and build together.

Machine Learning Engineer