Machine Learning Engineer

Mariana Minerals; Houston (TX); On-site; USD 120,000 - 180,000; Full time

Job summary

Mariana Minerals, based in Houston, TX, is building machine learning systems that help control mineral refining facilities and move toward fully autonomous refining operations.

You will work on reinforcement learning in physically realistic simulators, train control models, and connect simulation results to real plant data so improvements reach production. This onsite role offers a salary range USD 120,000 - 180,000 per year with experience starting at 2+ years.

Qualifications

• 2–8+ years of experience in ML/RL or related research.
• Solid grounding in machine learning fundamentals.
• Comfort reading and debugging an existing codebase in Python.
• Curiosity about physical, industrial systems.

Responsibilities

• Run RL experiments in realistic simulators and translate results into better controllers.
• Build and refine training environments, reward functions, observations, and action logic.
• Train control models and interpret performance; investigate underperformance.
• Close the gap between simulation and real plant data.
• Write clean, well-tested code and deploy models into production.
• Collaborate with process and chemistry experts to understand unit operations.

Skills

ML / RL experience

Python

Self-starter

Industrial systems

Job description

Mariana Minerals is building machine learning systems that help control mineral refining facilities and move toward fully autonomous refining operations. You will work on reinforcement learning in physically realistic simulators, train control models, and help connect simulation results to real plant data so improvements make it into production.

Based in Houston, TX, this is an onsite role with a salary range of USD 120,000 - 180,000 per year. Experience level starts at 2+ years.

What you’ll do

• Run reinforcement learning experiments in physically realistic simulators of mineral processing operations, then translate results into better controllers.
• Build and refine parts of training environments, including reward functions, observations, and action logic, with guidance from senior engineers.
• Train control models, track and interpret performance, and investigate causes when a model underperforms.
• 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 services that help deploy models into production.
• Partner with process and chemistry experts to understand the unit operations being modeled.

What makes the work challenging

• Our internal platform uses reinforcement learning toolkits similar to those used in self-driving vehicles and humanoid robots, 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.
• Training environments are noisy and non-stationary, with shifting wastewater compositions, changing ore grades, and equipment aging, requiring continuous adaptation.
• Training occurs inside physically realistic simulators of process units, followed by validation against real plant data before anything impacts live equipment.

What you bring

• 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 and working knowledge of modern deep learning; reinforcement learning exposure is a plus.
• Proficiency in Python and comfort reading and debugging an existing codebase.
• Curiosity about physical, industrial systems, with eagerness to learn chemistry and process engineering from experts who will challenge assumptions.
• A self-starter who asks good questions, ships work, and escalates blockers early.

Why this role

Mariana Minerals owns the projects, generates the data, and closes the loop. Each facility built makes the software smarter and helps the next facility move faster and cost less. Mining is one of the last major industrial sectors that has not been rebuilt with modern software, so this role centers on creating workflows and systems that do not yet exist. Your work will directly influence how critical minerals are produced at scale in the coming decades.

How we work

• 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 empower each other to build bigger, better solutions.