<div><span style="font-size:24px;">Role Overview </span></div><div><span style="font-size:16px;">Title: Senior Machine Learning Scientist (Surrogate modeling &amp; decision science in the earth sciences)</span></div><div><span style="font-size:16px;">Hours: Full-Time, Salaried</span></div><div><span style="font-size:16px;">Location: Salt Lake City, UT, Hybrid (3 days in office, 2 days can be remote)</span></div><div><span style="font-size:16px;">Benefits Eligible: Yes</span></div><div><span style="font-size:16px;">Manager: Head of Reservoir R&amp;D</span></div><div> </div><div><span style="font-size:18px;">Why we exist</span></div><div><span style="font-size:10pt;">Geothermal energy is the most abundant renewable energy source in the world. There is 2,300 times more energy in geothermal heat in the ground than in oil, gas, coal, and methane combined. However, historically it’s been hard to find and expensive to develop. At Zanskar, we’re building technology to find and develop new geothermal resources in order to make geothermal a cheap and vital contributor to a carbon-free electrical grid.</span></div><div> </div><div><span style="font-size:10pt;">To do that, we combine deep subsurface expertise with advanced AI technologies—including modern machine learning, scalable scientific computing, and uncertainty-aware modeling—to dramatically improve geothermal discovery and development outcomes. We build systems that can learn from sparse and noisy data, emulate expensive physics simulations, and help teams make faster, higher-confidence decisions about where to drill and how to develop fields.</span></div><div> </div><div><span style="font-size:18px;">Who you are</span></div><div><span style="font-size:10pt;">You will help build the modeling and decision-making core of Zanskar’s geothermal exploration software. This role blends scientific machine learning (surrogate modeling) with sequential decision-making under uncertainty. A successful candidate will:</span></div><div><span style="font-size:10pt;">Explore: you’re open-minded about methods and will prototype, benchmark, and iterate across approaches.</span></div><div><span style="font-size:10pt;">Reproduce &amp; adapt: you can implement ideas from papers and new frameworks quickly, then harden the best ones into reliable workflows.</span></div><div><span style="font-size:10pt;">Decision-minded: you care about end-to-end outcomes (value, risk, time-to-decision), not just model accuracy.</span></div><div><span style="font-size:10pt;">Uncertainty-first: you build models that are accurate, well-calibrated, and dependable under distribution shift and sparse data regimes.</span></div><div><span style="font-size:10pt;">Collaborative: you work well with domain experts and can translate between geology/engineering intuition and ML systems.</span></div><div> </div><div><span style="font-size:18px;">What you’ll do</span></div><div><span style="font-size:11pt;">Build fast, reliable models that emulate or augment computationally expensive physics-based simulations (e.g., reservoir, wellbore, and coupled multi-physics workflows).</span></div><div><span style="font-size:11pt;">Evaluate and compare multiple modeling approaches (physics-informed, operator learning, transformers, diffusion models, etc.), establishing strong baselines and selecting methods based on evidence.</span></div><div><span style="font-size:11pt;">Build multi-step decision systems for exploration and appraisal: POMDP-style planning and belief-space decision making to recommend exploration steps.</span></div><div><span style="font-size:11pt;">Translate scientific and engineering questions into well-defined learning and decision problems: inputs/outputs, constraints, boundary/initial conditions, reward/cost structure, and success metrics (e.g., expected NPV, probability of success, downside risk).</span></div><div><span style="font-size:11pt;">Prototype, benchmark, and iterate across approaches (POMDP solvers, RL methods, VOI-style baselines, MPC-style replanning), then harden the best ones into reliable workflows and APIs.</span></div><div><span style="font-size:11pt;">Collaborate deeply with geoscientists, reservoir engineers, and software engineers to integrate these models and policies into production software.</span></div><div> </div><div><span style="font-size:18px;">What we’re looking for</span></div><div><span style="font-size:11pt;">3+ years of applied ML experience, ideally in scientific ML, decision-making under uncertainty, surrogate modeling, robotics/control, or related engineering/science domains.</span></div><div><span style="font-size:11pt;">Expertise in python and modern ML tooling (PyTorch preferred).</span></div><div><span style="font-size:11pt;">Track record of taking models from prototype → rigorous evaluation → adoption by technical stakeholders.</span></div><div><span style="font-size:11pt;">Strong fundamentals in probability/statistics and comfort with messy, real-world scientific datasets.</span></div><div><span style="font-size:11pt;">Experience building or using surrogate models for expensive simulators (PDE-driven systems, multi-physics, or similar).</span></div><div><span style="font-size:10pt;">Relevant technical strengths</span></div><div><span style="font-size:11pt;">Surrogate modeling. </span></div><div><span style="font-size:11pt;">Sequential decision-making under uncertainty and reinforcement learning. </span></div><div><span style="font-size:11pt;">Software engineering: Git, code review, reproducibility, CI basics, Docker/container workflows.</span></div><div><span style="font-size:11pt;">Experience with diffusion models.</span></div><div><span style="font-size:11pt;">Exposure to subsurface modeling domains: geothermal, oil &amp; gas, CCS, hydrogeology, geoscience, or related.</span></div><div><span style="font-size:11pt;">Familiarity with cloud infrastructure and data systems (SQL, object storage, orchestration).</span></div><div> </div><div><span style="font-size:18px;">Location and Benefits</span></div><div><span style="font-size:10pt;">This position is based out of our headquarters in </span><strong style="font-size:10pt;">Salt Lake City, Utah</strong><span style="font-size:10pt;">, and is </span><strong style="font-size:10pt;">hybrid</strong><span style="font-size:10pt;">.</span></div><div><span style="font-size:10pt;">Benefits include:</span></div><div><span style="font-size:10pt;">Paid holidays</span></div><div><span style="font-size:10pt;">15 days PTO + PTO accrual increase based on tenure</span></div><div><span style="font-size:10pt;">Medical, dental and vision coverage</span></div><div><span style="font-size:10pt;">401k </span></div><div><span style="font-size:10pt;">Stock options</span></div><div><span style="font-size:10pt;">Growth opportunities at a company with a direct impact in displacing carbon emissions</span></div><br><br><br><div><span style="font-size:12pt;">Equal Opportunity Employer </span></div><div> </div><div><span style="font-size:10pt;">Zanskar is an equal-opportunity employer and complies with all applicable federal, state, and local fair employment practice laws.</span></div>

<p>It is our mission to make geothermal power the most affordable form of widely-deployable, 24/7, carbon-free energy generation on the planet.&nbsp;</p>

Senior Machine Learning Scientist

<div><span>Role Overview </span></div><div><span>Title: Senior Machine Learning Scientist (Surrogate modeling &amp; decision science in the earth sciences)</span></div><div><span>Hours: Full-Time, Salaried</span></div><div><span>Location: Salt Lake City, UT, Hybrid (3 days in office, 2 days can be remote)</span></div><div><span>Benefits Eligible: Yes</span></div><div><span>Manager: Head of Reservoir R&amp;D</span></div><div> </div><div><span>Why we exist</span></div><div><span>Geothermal energy is the most abundant renewable energy source in the world. There is 2,300 times more energy in geothermal heat in the ground than in oil, gas, coal, and methane combined. However, historically it’s been hard to find and expensive to develop. At Zanskar, we’re building technology to find and develop new geothermal resources in order to make geothermal a cheap and vital contributor to a carbon-free electrical grid.</span></div><div> </div><div><span>To do that, we combine deep subsurface expertise with advanced AI technologies—including modern machine learning, scalable scientific computing, and uncertainty-aware modeling—to dramatically improve geothermal discovery and development outcomes. We build systems that can learn from sparse and noisy data, emulate expensive physics simulations, and help teams make faster, higher-confidence decisions about where to drill and how to develop fields.</span></div><div> </div><div><span>Who you are</span></div><div><span>You will help build the modeling and decision-making core of Zanskar’s geothermal exploration software. This role blends scientific machine learning (surrogate modeling) with sequential decision-making under uncertainty. A successful candidate will:</span></div><div><span>Explore: you’re open-minded about methods and will prototype, benchmark, and iterate across approaches.</span></div><div><span>Reproduce &amp; adapt: you can implement ideas from papers and new frameworks quickly, then harden the best ones into reliable workflows.</span></div><div><span>Decision-minded: you care about end-to-end outcomes (value, risk, time-to-decision), not just model accuracy.</span></div><div><span>Uncertainty-first: you build models that are accurate, well-calibrated, and dependable under distribution shift and sparse data regimes.</span></div><div><span>Collaborative: you work well with domain experts and can translate between geology/engineering intuition and ML systems.</span></div><div> </div><div><span>What you’ll do</span></div><div><span>Build fast, reliable models that emulate or augment computationally expensive physics-based simulations (e.g., reservoir, wellbore, and coupled multi-physics workflows).</span></div><div><span>Evaluate and compare multiple modeling approaches (physics-informed, operator learning, transformers, diffusion models, etc.), establishing strong baselines and selecting methods based on evidence.</span></div><div><span>Build multi-step decision systems for exploration and appraisal: POMDP-style planning and belief-space decision making to recommend exploration steps.</span></div><div><span>Translate scientific and engineering questions into well-defined learning and decision problems: inputs/outputs, constraints, boundary/initial conditions, reward/cost structure, and success metrics (e.g., expected NPV, probability of success, downside risk).</span></div><div><span>Prototype, benchmark, and iterate across approaches (POMDP solvers, RL methods, VOI-style baselines, MPC-style replanning), then harden the best ones into reliable workflows and APIs.</span></div><div><span>Collaborate deeply with geoscientists, reservoir engineers, and software engineers to integrate these models and policies into production software.</span></div><div> </div><div><span>What we’re looking for</span></div><div><span>3+ years of applied ML experience, ideally in scientific ML, decision-making under uncertainty, surrogate modeling, robotics/control, or related engineering/science domains.</span></div><div><span>Expertise in python and modern ML tooling (PyTorch preferred).</span></div><div><span>Track record of taking models from prototype → rigorous evaluation → adoption by technical stakeholders.</span></div><div><span>Strong fundamentals in probability/statistics and comfort with messy, real-world scientific datasets.</span></div><div><span>Experience building or using surrogate models for expensive simulators (PDE-driven systems, multi-physics, or similar).</span></div><div><span>Relevant technical strengths</span></div><div><span>Surrogate modeling. </span></div><div><span>Sequential decision-making under uncertainty and reinforcement learning. </span></div><div><span>Software engineering: Git, code review, reproducibility, CI basics, Docker/container workflows.</span></div><div><span>Experience with diffusion models.</span></div><div><span>Exposure to subsurface modeling domains: geothermal, oil &amp; gas, CCS, hydrogeology, geoscience, or related.</span></div><div><span>Familiarity with cloud infrastructure and data systems (SQL, object storage, orchestration).</span></div><div> </div><div><span>Location and Benefits</span></div><div><span>This position is based out of our headquarters in </span><strong>Salt Lake City, Utah</strong><span>, and is </span><strong>hybrid</strong><span>.</span></div><div><span>Benefits include:</span></div><div><span>Paid holidays</span></div><div><span>15 days PTO + PTO accrual increase based on tenure</span></div><div><span>Medical, dental and vision coverage</span></div><div><span>401k </span></div><div><span>Stock options</span></div><div><span>Growth opportunities at a company with a direct impact in displacing carbon emissions</span></div><br /><br /><br /><div><span>Equal Opportunity Employer </span></div><div> </div><div><span>Zanskar is an equal-opportunity employer and complies with all applicable federal, state, and local fair employment practice laws.</span></div>

Senior Machine Learning Scientist

About the Job

About the Company

Zanskar

Similar Jobs

Machine Learning Engineer, Staff or Principal

Machine Learning Engineer, Staff or Principal

Senior Machine Learning Infrastructure Engineer

Senior Machine Learning Infrastructure Engineer

Senior Data Engineer

Senior Data Engineer

Staff Scientist – Post-Training and Reinforcement Learning for AI for Science

Staff Scientist – Post-Training and Reinforcement Learning for AI for Science

Senior MLOps & Data Systems Engineer

Senior MLOps & Data Systems Engineer

Senior MLOps & Data Systems Engineer

Senior MLOps & Data Systems Engineer

Senior Machine Learning Engineer

Senior Machine Learning Engineer

Staff Applied Scientist

Staff Applied Scientist

Senior Data Scientist, Machine Learning

Senior Data Scientist, Machine Learning

Senior Staff Machine Learning Engineer

Senior Staff Machine Learning Engineer