Senior Data Scientist, Physics-Based Modeling & Equipment Reliability
Reports to: Data Science Manager
Location: Houston, TX (oully onsite)
Brief Description:
The Completions Data Science team brings together talented, driven professionals who turn complex operational data into clear insights and empowers our client to make smarter, data-backed decisions every day.
You will work specifically with Operations and Maintenance departments to develop physics-driven models and reliability frameworks that predict equipment behavior and optimize maintenance strategies for the frac fleet.
Detailed Description:
In this role you will collaborate with Program Managers to lead the strategy and execution of hybrid physics and machine-learning models for equipment reliability.
You will design and run first-principles simulations, integrate high-frequency telemetry into digital twins, deploy scalable model pipelines in the cloud and validate predictions against field data.
Key Responsibilities:
Define and guide the development of physics-ML reliability models (Weibull analysis, survival modeling, FMEA)
Perform fluid-mechanics and mechanical simulations in Python or MATLAB and integrate outputs with telemetry streams
Architect, deploy and monitor model training and serving pipelines on GCP AI Platform or Dataiku
Establish validation protocols by coordinating with subject-matter experts to calibrate model assumptions
Partner with maintenance, operations and field teams to align modeling efforts with business needs and data availability
Identify new digital-twin use cases and build proof-of-concepts for early-warning systems and maintenance optimization
Present technical findings to operations leadership, maintenance planners and engineering management
Job Requirements:
Prior experience in equipment reliability, predictive maintenance or physics-based modeling in oil and gas
Expert programming skills in Python (SciPy, NumPy) for simulation and model development
Strong foundation in reliability engineering methods such as Weibull analysis, survival modeling and FMEA
Strong communication skills with the ability to explain complex models to non-technical stakeholders
Ability to manage multiple priorities and deliver results on time
Minimum Qualifications:
Bachelor's degree in Mechanical Engineering, Petroleum Engineering, Physics or related field
5+ years of experience applying physics-based modeling or reliability engineering in industrial settings
3+ years building and deploying data-science algorithms on cloud platforms (AWS, GCP or Azure)
3+ years developing simulation code in Python
Preferred Qualifications:
Master's degree or higher in a quantitative engineering or physical science discipline
Research publications or patents in equipment reliability, preventative maintenance or related areas
Prior field experience in equipment maintenance
Experience integrating physics-based models with machine-learning frameworks such as TensorFlow or PyTorch