BC Sector O and G-Data Scientist-Manager

At EY, you’ll have the chance to build a career as unique as you are, with the global scale, support, inclusive culture and technology to become the best version of you. And we’re counting on your unique voice and perspective to help EY become even better, too. Join us and build an exceptional experience for yourself, and a better working world for all.
EY GDS | LEAD DATA SCIENTIST
Oil & Gas | Manager
Job Title Lead Data Scientist – Manager
Job Description
At EY, you’ll have the chance to build a career as unique as you are, with the global scale, support, inclusive culture and technology to become the best version of you. We’re counting on your unique voice and perspective to help EY become even better. Join us and help build a better working world.
We are looking for a hands-on Data Scientist to develop analytical and machine learning solutions used by petroleum, drilling, production, process and reliability engineers. You will work with operational and engineering data to diagnose performance, predict outcomes and support better operating decisions across upstream and downstream assets.
Role Details
Key responsibilities include:
Upstream data science
Develop analytical solutions for well-performance surveillance, production forecasting, artificial-lift diagnostics and equipment-health monitoring.
Analyse drilling data to identify operating states, evaluate rate-of-penetration performance and detect patterns associated with dysfunctions or non-productive time.
Work with production rates, well tests, pressure and temperature measurements, choke settings, lift-system parameters and intervention histories.
Distinguish measured, tested and allocated production, accounting for shut-ins, interventions and operating-strategy changes.
Support well-log and reservoir-related modelling with geoscience and reservoir specialists where relevant.
Downstream data science
Develop inferential models and soft sensors for product quality, unit yields and process performance.
Analyse heat-exchanger fouling, rotating-equipment condition, catalyst-performance trends, and energy or utility consumption.
Work with process historians, laboratory systems, online analyzers, crude assays, maintenance records and simulation outputs.
Align laboratory results with sample time and process residence time, distinguishing steady operation from start-ups, shutdowns, and grade or feedstock changes.
Support blending, process optimization and planning using predictive models and appropriately constrained analytical methods.
Model development and technical delivery
Define engineering objectives, prediction horizons, target variables, operating boundaries and acceptance criteria with domain specialists.
Assess data quality, sampling bias, confounding, missing measurements, lineage and suitability; perform exploratory analysis, hypothesis testing and uncertainty estimation.
Engineer domain-informed features and develop statistical, machine learning and time-series models for regression, classification, clustering, forecasting, anomaly and change-point detection.
Establish defensible baselines and time-aware or grouped validation, preventing leakage and addressing autocorrelation, non-stationarity, imbalance, sparse labels and changing conditions.
Evaluate using application-relevant measures, apply explainability and uncertainty methods, and use deep learning only where justified against simpler alternatives.
Build reproducible training and inference pipelines; track experiments and monitor data quality, drift, predictive performance and training-serving consistency.
Document assumptions, applicability limits, validation and retraining triggers; review code and guide other data scientists.
Expected technical stack
Strong hands-on Python and SQL.
Practical experience with pandas, NumPy, SciPy, scikit-learn, statistical modelling libraries and at least one gradient-boosting framework.
Experience with version control, automated testing, experiment tracking, model registries, deployment workflows and model monitoring.
Familiarity with PyTorch or TensorFlow where deep learning is appropriate.
Must Have Qualifications & Experience
A degree in petroleum, chemical, mechanical or another relevant engineering discipline, statistics, mathematics, computer science or data science.
Demonstrated hands-on delivery of Oil & Gas analytical solutions, with strong experience in at least one upstream or downstream domain and working understanding of the other.
Strong foundations in statistics, regression, classification, time-series analysis, feature engineering, model evaluation and uncertainty estimation.
Experience with irregular sampling, missing measurements, limited failure labels, changing operating conditions and multiple operational regimes.
Evidence of personal contribution across data assessment, development, deployment and operational monitoring.
Experience leading or reviewing data scientists’ technical work and collaborating with engineering and technology teams.
Good to Have
Experience delivering analytical solutions across both upstream and downstream environments.
Specialist depth in signal processing, reliability modelling, constrained optimization, subsurface analytics, or hybrid engineering and ML methods.
Familiarity with well-data formats, industrial historians, laboratory systems and engineering simulators.
Experience with cloud ML platforms or edge inference.
Experience applying NLP, retrieval-augmented generation or agentic workflows to engineering information and analytical tools.
What We Offer
Opportunity to solve high-impact industrial data and analytics challenges across upstream and downstream Oil & Gas.
A hands-on leadership role with scope to establish reusable practices and guide multidisciplinary teams.
A collaborative environment spanning domain engineering, data, technology, product and global EY teams.
Access to EY’s global network, technology ecosystem and learning opportunities while contributing to a better working world.
What We Look For
A Data Scientist who can walk through a real industrial modelling problem and clearly explain the data, engineering assumptions, baseline, feature design, validation, deployment behaviour, business relevance and model limitations, while evidencing personal technical contribution and ability to lead others.
EY | Building a better working world
EY exists to build a better working world, helping to create long-term value for clients, people and society and build trust in the capital markets.
Enabled by data and technology, diverse EY teams in over 150 countries provide trust through assurance and help clients grow, transform and operate.
Working across assurance, consulting, law, strategy, tax and transactions, EY teams ask better questions to find new answers for the complex issues facing our world today.

Work arrangement
No