Machine Learning Engineer

Join Mariana Minerals in Houston to build machine learning systems that help control mineral refining facilities and move toward fully autonomous refining operations.

• Run reinforcement learning experiments in physically realistic simulators for mineral processing operations, then translate results into improved controllers
• Build and iterate training environments, including reward functions, observations, and action logic, with guidance from senior engineers
• Train and evaluate control models, monitor performance, and investigate underperformance causes
• Close the sim-to-reality gap by comparing model behavior to real plant data and flagging where physics diverges
• Deliver production-ready code with clean implementation and testing, contributing to services that deploy models
• Collaborate with domain experts in process and chemistry to model unit operations accurately

Requirements

• 2-8+ years of experience in machine learning, reinforcement learning, or scientific computing (internships or research included) or a strong recent graduate with demonstrated project depth
• Solid ML fundamentals with working knowledge of modern deep learning; reinforcement learning experience is a strong plus
• Python proficiency and comfort reading and debugging an existing codebase
• Interest in physical and industrial systems, plus eagerness to learn chemistry and process engineering from experts who will challenge assumptions
• Self-starter mindset who asks good questions, ships work, and escalates blockers early

Tech and Tools

• Python
• Reinforcement learning
• Deep learning

The Tech

• Internal platform uses reinforcement learning toolkits similar to those used for 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 to optimize simultaneously across lithium recovery, reagent consumption, energy intensity, and equipment uptime
• Training conditions are noisy and non-stationary: wastewater compositions shift, ore grades change, and equipment ages; models must continuously adapt
• End goal is fully autonomous refining operations
• Training occurs inside physically realistic simulators of process units, followed by comparison against real plant data before any live deployment

Role Details

• Location: Houston, TX (onsite)
• Compensation: USD 120,000 - 180,000 per year
• Minimum experience: 2 years

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 and share knowledge to build bigger solutions