Job Purpose
We are seeking a highly skilled and motivated Data Scientist to join our Reservoir and Production Technology team. The ideal candidate will work at the intersection of data science, reservoir engineering, and production operations, leveraging advanced analytics, machine learning, and statistical modelling to optimize hydrocarbon recovery, production efficiency, and field development strategies. This role is crucial in driving data-driven decision-making by integrating subsurface data (logs, core, seismic), production data (rates, pressures, downtime), and surface facility data (flowlines, choke settings, sensors).
Key Responsibilities
- Develop predictive models for reservoir performance forecasting, decline curve analysis, and production optimization
- Apply machine learning algorithms (e.g. random forests, gradient boosting, time
- series models, deep learning) to identify patterns in production and performance data
- Integrate diverse datasets (PVT, SCADA, seismic, well logs, simulation outputs) to create actionable insights for reservoir management
- Collaborate with reservoir engineers, geologists, and petroleum engineers to design data-enabled workflows
- Support real-time data analytics and build dashboards for operational surveillance and anomaly detection
- Participate in digital transformation initiatives and help implement AI/ML tools in the field and corporate settings
- Ensure data quality, cleaning, normalization, and management of large datasets using appropriate data engineering tools
- Provide statistical insights during field development planning, well intervention analysis, and history matching support
- Stay attuned to industry trends and new technologies in petroleum data science and reservoir digitalization
Requirements
Required Qualifications:
- Master’s or PhD in Data Science, Applied Mathematics, computing science, or related field
- 3+ years of experience in data science, preferably within the oil and gas industry
- Strong command of Python, SQL, and at least one ML framework (e.g. sci-kit-learn, TensorFlow, PyTorch)
- Experience with data visualization tools (e.g. Power BI, Spotfire, Dash, Tableau)
- Knowledge of statistics, time-series analysis, uncertainty quantification, and optimization techniques
- Fluency in English
- Experience with cloud platforms (AWS, Azure) and big data tools (e.g. Spark, Hadoop)
- Familiarity with reservoir simulation software (e.g. Eclipse, CMG, tNavigator)
- Familiarity with reservoir simulation output, production databases (OFM, IPM), and field instrumentation data
- Exposure to well-performance modelling, nodal analysis, or formation evaluation is a plus
- Understanding of flow assurance and production system modelling concepts
- Strong analytical and problem-solving skills
- Effective communication and interdisciplinary collaboration
- Attention to detail and ability to work with large, complex datasets
- Self-starter with a passion for continuous learning and innovation
*Only applicants meeting the strict criteria outlined above will be contacted as part of the shortlisting process.