Machine Learning Engineering Manager, Chemistry & Process Engineering

3 нед. назад

176k–212k USD / годСШАLeadOnsite

machine learningprocess modelingchemistrydata analysisoptimizationcontrol systems

Manage a team of machine learning engineers building models for chemistry and process engineering in a minerals company.

О компании

Mariana Minerals is a software-first, vertically integrated minerals company on a mission to supply the critical minerals powering modern energy, AI, and defense technologies. We’re reimagining the minerals supply chain by combining deep industry expertise with advanced software, automation, and data-driven decision-making.
Everyone Gets Home Safe. We never put speed or cost ahead of people.
Extreme Ownership. We take full responsibility for outcomes, relentlessly driving toward solutions.
Engineer Out Requirements, then Automate. We simplify, optimize, and then automate for scale.
Share Your Legos. We collaborate openly, share knowledge, and empower each other to build bigger, better solutions.

Обязанности

Mariana Minerals is a software-first, vertically integrated minerals company supplying the minerals critical to modern energy, AI, and defense technologies. Our ML systems don't live in a vacuum — they learn from and run alongside chemistry and process simulators, and they increasingly inform, and set, how our plants and chemical processes operate.
We're hiring a Machine Learning Engineering Manager to lead the team of MLEs building models for chemistry and process engineering: surrogate and hybrid models of unit operations, models that learn from plant and lab data, and the optimization and control layers that turn those models into operating decisions. You'll manage the people, own the technical quality of what ships, and partner with the Technical Product Manager for ML & Robotics on what gets built and why.
This is a player-coach role. Today this work is done by strong individual MLEs with technical leads setting direction informally. Your job is to make it a team: hire the next several engineers, set the engineering and modeling bar, and give the TPM a counterpart who can say what is technically possible, how long it will take, and what it will cost in accuracy or risk.
Manage, coach, and grow a team of ML engineers working on chemistry and process problems — hiring, onboarding, 1:1s, performance reviews, career development, and the hard conversations when they're needed.
Own the technical direction of the team: model architectures, data strategy, validation methodology, and the standards for when a model is trusted enough to inform or set a process decision.
Partner with a TPM on the roadmap: translate product priorities into scoped engineering work, push back when the ask isn't feasible, and commit to what the team will deliver.
Work directly with process engineers, chemists, and operators to make sure the models the team builds answer the questions the plant actually has.
Set the bar for rigor in a domain where physics matters: mass and energy balances, thermodynamic consistency, extrapolation limits, uncertainty quantification, and the difference between a model that fits and a model that's right.
Own the production lifecycle of the team's models — deployment, monitoring, retraining, drift, and incident response — and the operational practices (on-call, runbooks, review) that keep them reliable.
Run the team's engineering practices: code and model review, experiment tracking, reproducibility, and documentation, so work survives the person who built it.
Stay hands-on enough to review the hardest work, unblock engineers, and prototype when the fastest path to an answer is to build it yourself.
Own headcount planning and hiring for the team, and build the pipeline of ML engineers with chemistry and process backgrounds.

Требования

6+ years in machine learning or scientific computing, including 2+ years managing ML engineers or scientists with direct responsibility for hiring, performance, and growth.
Degree or equivalent depth in chemical engineering, chemistry, materials science, or a closely related field — you can read a process flow diagram, reason about reaction kinetics and separations, and hold your own with process engineers.
Hands-on track record shipping ML models to production for physical, scientific, or industrial systems: surrogate models, hybrid physics-ML models, time-series forecasting, Bayesian optimization, or similar.
Strong engineering fundamentals: Python, modern ML frameworks, experiment tracking, and the discipline to make research code reproducible and maintainable.
Track record of setting technical direction for a team and delivering against commitments in an ambiguous, cross-functional environment.
Ability to evaluate work you didn't do — you can review a model, spot the flaw in a validation approach, and give feedback that makes the engineer better.
Exceptional written and verbal communication across audiences, from ML engineers to process engineers to operators to executives.

Будет плюсом

PhD in chemical engineering, chemistry, or materials science with an ML or computational focus.
Experience with model predictive control, real-time optimization, or other closed-loop optimization of chemical or industrial processes.
Background in mining, hydrometallurgy, energy, chemicals, or other heavy industry.
Experience building a team from a handful of engineers to a functioning organization.

Другое

Player-coach: You spend most of your time on people, priorities, and quality — and enough time in the code and the data to keep your judgment sharp.
Structure from ambiguity: Turn loosely defined process problems into scoped modeling work with clear success criteria, and align process engineers, MLEs, and product behind it.
Physics-literate skepticism: You know when a model is learning chemistry and when it's learning an artifact, and you hold the team to the former.
Clear commitments: Give the TPM and the business honest estimates, visible tradeoffs, and early warning when something is slipping.
Ecosystem fluency: Understand where the team's models sit relative to the simulators, the data platform, and the control systems that consume them, so nothing falls in the gap.
Most ML manager roles hand you a mature team and a model with a defined scope. This role hands you the models that will increasingly run our chemistry and process operations, a team that's ready to be built, and a company where the plant is down the hall. At Mariana, you don't need to validate product-market fit, because we are the market: if your team builds a model that makes the process run better, it goes into the process.