Location: Houston preferred
💼 The RoleWe are looking for a reservoir engineer with strong technical curiosity and an interest in programming, machine learning, and applied data science to help develop the next generation of whitsonX machine learning models.
This role sits at the intersection of reservoir engineering, product development, and machine learning. You will work closely with the whitsonX product team, our technical team, 20+ consortium member companies, and selected operator partners to translate real field problems into scalable ML-driven workflows.
The work will include building, testing, and improving models related to unconventional well performance, depletion, parent-child effects, spacing, inventory quality, type wells, forecasting, and other operator-driven workflows. A strong example of the type of work is our approach to predicting child well performance degradation using neural networks, parent/child geometry, depletion intensity, and basin-scale datasets.
🔥 What You'll DoYou will help develop and improve machine learning models inside whitsonX by combining engineering judgment, operator feedback, and data-driven methods.
- Develop, test, and validate machine learning models for well performance prediction, depletion, spacing, inventory, and other whitsonX workflows.
- Work closely with the product team to turn technical models into intuitive, scalable software features.
- Collaborate directly with 20+ consortium member companies to understand their workflows, pain points, and desired features.
- Work with specific operator partners to incorporate domain knowledge, field-specific behavior, and requested functionality into whitsonX models.
- Analyze large production, completion, spacing, geologic, and well performance datasets.
- Translate reservoir engineering concepts into model inputs, features, diagnostics, and product requirements.
- Evaluate model performance, identify limitations, and communicate uncertainty clearly.
- Help design workflows that are technically rigorous but simple enough for engineers to use in day-to-day asset development decisions.
- Write clear technical documentation, examples, and internal notes explaining how models work.
- Support customer-facing technical discussions when needed, especially with reservoir, production, and development teams.
🌱 Ideal Background We are looking for someone who has worked as an engineer at an operator and has a genuine interest in building better technical software.
- 5-15 years of experience with an oil and gas operator, preferably in reservoir engineering, production engineering, development planning, A&D, or subsurface analytics.
- Strong understanding of unconventional reservoir development.
- Familiarity with topics such as type wells, well spacing, depletion, parent-child effects, completions, forecasting, and economic development decisions.
- Interest in programming and willingness to become highly proficient.
- Basic understanding of statistics, data science, or machine learning.
- Experience with Python is a plus.
- Ability to work with messy field data and still ask the right engineering questions.
- Excellent written and spoken English.
- Strong communication skills and comfort working directly with customers.
- Curious, practical, and excited about combining engineering intuition with modern software and machine learning.
✅ What makes someone successful in this roleThe best person for this role is not necessarily a pure data scientist or a pure reservoir engineer. We are looking for someone who can connect both worlds.
You should enjoy asking questions like:
- Does the model make engineering sense?
- What feature would actually help an operator make a better decision?
- What data is trustworthy enough to use?
- How should uncertainty be shown to the user?
- How do we turn a customer request into something scalable for the whole product?
You should be comfortable working in a fast-moving environment where models, workflows, and product features are constantly improving based on customer feedback.
⚡ Why this role is excitingThis is a unique opportunity to help build ML models that are not just research projects, but actively used by operators to make real development decisions.
You will work directly with the product team, customers, and consortium members to shape what whitsonX becomes. The goal is not to build black-box models in isolation. The goal is to build practical, explainable, engineering-driven machine learning workflows that help operators make better decisions faster.
🧠 Nice-to-have experience- Experience with two or more unconventional plays.
- Experience with parent-child analysis, spacing studies, or development optimization.
- Experience building or validating type curves.
- Experience using Python for data analysis.
- Experience working with large operator datasets.
- Experience presenting technical work to internal or external stakeholders.
- Publications, SPE papers, internal studies, or technical presentations are a plus but not required.
How to applySend your CV and a brief introduction describing why you’d be a great fit for this to jessica@whitson.com
Applications close August 31, 2026.