Product Manager, PlantOS
About Mariana Minerals
Mariana Minerals is not a software company selling to mining companies. We are a mining company that builds software.
We design, build, commission, and operate our own mines and refineries. We develop our own chemical processes. We're producing battery-grade lithium salts from real oil and gas wastewater in our lab and pilot facilities today. Our first commercial-scale lithium production facility, Lithium One, is targeting production in the first half of 2027.
The software — what we call MarianaOS — exists to make our projects come online faster and run better. We don't sell it. We deploy it into our own operations and measure its impact in tons of metal produced, dollars of cost removed, and months shaved off construction timelines.
Role Overview
We're looking for a Product Manager to own PlantOS — Mariana's autonomy platform for mineral processing facilities.
PlantOS uses the same reinforcement learning toolkit powering self-driving vehicles and humanoid robots — except we're using it for autonomous, short-interval control of minerals refining circuits. We adjust operating set points in real time, optimizing across lithium recovery, reagent consumption, energy intensity, and equipment uptime simultaneously. The feedstock is variable and messy — wastewater compositions shift, ore grades change — and the system has to adapt continuously. We're targeting a 50% compression in commissioning timelines and a 25%+ reduction in steady-state operating costs.
Ship a feature here and you can watch the needle move — recovery rates, reagent consumption, energy intensity, equipment uptime. These aren't proxy metrics. They're the actual physics of making metal.
You'll work with chemical engineers, metallurgists, ML engineers, and plant operators — people who understand the physics of what they're doing and can tell you exactly where the bottlenecks are. There's no translation layer between you and the domain experts. They're your direct collaborators. They'll push back on your designs with real constraints and tell you when your model is wrong and why.
The Product: PlantOS
PlantOS is Mariana's autonomy platform for fixed-plant mineral processing. It's the system that controls and optimizes everything that happens inside a processing facility—lithium refining, solvent extraction and electrowinning (SX-EW), grinding, flotation, and beyond.
What PlantOS does:
Exposes all the information (everything from design drawings to PLC data) needed to manage a facility in one easy to navigate location — and directs operator attention to the most relevant metrics to drive continuous improvement
Uses reinforcement learning to dynamically adjust operating conditions in real-time, responding to feed variability and process upsets
Optimizes recovery, throughput, energy consumption, and reagent usage simultaneously across different process types
Accelerates facility ramp-up by encoding operational expertise into software
Moves toward no-human-in-the-loop operations for routine process control
Mineral processing is a complex dance of chemistry and physics — dozens of interdependent variables where small adjustments compound into major differences in yield, quality, and cost. PlantOS is how we run processing facilities smarter than anyone else.
What You'll Do
Define what to build by looking at operational performance data and talking to operators and process engineers — including figuring out what metrics and instrumentation need to exist in the first place
Spend 25-50% of your time at processing facilities, learning how the process chemistry works, observing operators making real-time decisions, and understanding where software can change outcomes
Bridge very different stakeholders: PhD chemists and process engineers who think in thermodynamics, plant operators who know what's working and what isn't, and ML engineers building the control models
Ship software that runs in production environments controlling real equipment — where bugs have physical and financial consequences
Work with domain experts and ML engineers to identify where reinforcement learning can improve recovery, throughput, or efficiency — and define how the system should behave when conditions change
What We're Looking For
Must Have
4-7 years in product management, with experience in industrial, manufacturing, or heavy industry software
Intellectual curiosity about physical systems — you want to understand how flotation circuits work and why reagent dosing matters, not just treat the domain as a black box
Ability to communicate across a huge range of technical literacy — from PhD chemists and process engineers to plant operators with no software background
Experience working on data-intensive or ML-powered products
Demonstrated ability to ship products in complex technical environments
Nice to Have
Experience with process control, SCADA/DCS systems, or industrial automation
Familiarity with reinforcement learning or ML-based optimization
Background in chemical engineering, metallurgy, or process engineering
Why This Role
Process control in mineral processing has been largely unchanged for decades — PID loops and human operators making adjustments based on experience and intuition. ML-based control is the next frontier, but most industrial companies are too conservative to pursue it aggressively. Almost everything here is greenfield. We're not improving an existing product by 10%. We're building systems that didn't exist before.
At Mariana, you don't need to validate product-market fit because we are the market. If you identify a real problem and build a real solution, adoption is a conversation, not a sales cycle. The constraint is building the right thing, not convincing someone to buy it.
This role is for the PM who wants to watch RL algorithms make real-time physical decisions — adjusting reagent flows, shifting operating set points, responding to feed variability — and see the results in actual recovery rates and cost curves, not A/B test dashboards. You'll build the software that runs lithium refineries, SX-EW plants, and flotation circuits. The goal is fully autonomous refining operations with no human in the loop. If you want to work on applied AI at its most concrete — not another recommendation engine or chatbot wrapper — this is it.
What It's Like to Work Here
Extreme Ownership – We take full responsibility for outcomes and drive relentlessly toward solutions.
Engineer Out, Then Automate – We simplify and optimize before we scale.
Share Your Legos – We collaborate openly, share knowledge freely, and help each other build better solutions.
Mariana is an Equal Opportunity Employer. We celebrate diversity and are committed to creating an inclusive environment for all employees. We do not discriminate on the basis of race, color, religion, sex, sexual orientation, gender identity, national origin, age, disability, veteran status, or any other protected status.