Mariana Minerals is building machine learning systems that help control mineral refining facilities and move toward fully autonomous refining operations. This role blends reinforcement learning with physically realistic simulation, model training, and on-the-ground validation against real plant data so improvements translate into production-ready controllers.
You will work on an internal platform that uses reinforcement learning toolkits similar to those behind 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 across lithium recovery, reagent consumption, energy intensity, and equipment uptime simultaneously.
Responsibilities
- Run reinforcement learning experiments in physically realistic simulators of mineral processing operations and turn results into improved controllers.
- Build and refine training environments, including reward functions, observations, and action logic, with guidance from senior engineers.
- Train control models, track and interpret their performance, and investigate causes when models underperform.
- Close the gap between simulation and reality by comparing model behavior against real plant data and flagging where physics diverges.
- Write clean, well-tested code and contribute to the services that deploy models into production.
- Partner with process and chemistry experts to understand the unit operations being modeled.
What You’ll Be Working With
Training happens inside physically realistic simulators of process units, followed by validation against real plant data before models impact live equipment. The environment is intentionally challenging: it is noisy and non-stationary, with wastewater compositions shifting, ore grades changing, and equipment aging. The system must continuously adapt as conditions evolve.
Requirements
- 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.
- Strong ML fundamentals with working knowledge of modern deep learning; reinforcement learning experience is a strong plus.
- Proficiency in Python and comfort reading and debugging an existing codebase.
- Curiosity about physical, industrial systems, plus willingness to learn chemistry and process engineering from experts who will challenge assumptions.
- A self-starter mindset: ask good questions, ship, and escalate blockers early.
Tech Stack
- Python
- Reinforcement learning
- Deep learning
Why This Role
- Own the loop: projects, data generation, and the path from simulation to real operations.
- Build workflows that don’t exist yet: mining is one of the last major industrial sectors without modern software rebuilt into complete systems.
- High-impact, long-horizon work: directly shape how critical minerals are produced at scale in the coming decades.
Culture
- Extreme Ownership: full responsibility for outcomes, with relentless drive toward solutions.
- Engineer Out Requirements, then Automate: simplify, optimize, and automate for scale.
- Share Your Legos: open collaboration and shared knowledge to build bigger, better solutions.
Location: Houston, TX (onsite). Compensation: USD 120,000 - 180,000 per year. Experience: 2 years minimum.
