Machine Learning Engineer

Machine Learning Engineer role at Mariana Minerals in Ann Arbor focused on building reinforcement learning systems that learn in realistic simulators and perform against real mineral refining plant data.

Responsibilities

• Run reinforcement learning experiments in physically realistic simulators of mineral processing operations and translate results into improved controllers
• Build and iterate components of training environments, including reward functions, observations, and action logic, with input from senior engineers
• Train control models, track and interpret performance, and investigate why a model underperforms
• Close the simulation-to-reality gap by comparing model behavior to 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 and model unit operations

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
• Solid grounding in machine learning fundamentals and 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 and eagerness to learn chemistry and process engineering from experts who will challenge assumptions
• Self-starter mindset: ask strong questions, ship work, and escalate blockers early

Technologies

• Python

The Tech

• Uses reinforcement learning toolkits commonly used in self-driving vehicles and humanoid robots, adapted for autonomous, short-interval control of mineral refining circuits
• Control models adjust operating set points and configurations in real time to optimize across lithium recovery, reagent consumption, energy intensity, and equipment uptime simultaneously
• Trains control models inside physically realistic simulators, then closes the gap by validating against real plant data before any models touch live equipment

Compensation

• $120,000 - $180,000 per year

Culture

• Extreme Ownership – full responsibility for outcomes and relentless focus on solutions
• Engineer Out Requirements, then Automate – simplify, optimize, and automate for scale
• Share Your Legos – collaborate openly, share knowledge, and enable bigger, better solutions