Data Scientist
HybridHouston, Texas, United States
Job Summary
Leverage strong data science skills throughout the analysis process, including problem formulation, aggregation, transformation, cleaning, descriptive analysis, modeling, visualization, and presentation. Design and execute research on open-ended problems related to data analytics, machine learning, and predictive modeling on large, complex datasets to draw insights for key stakeholders. Evaluate, improve, and invent analysis methods for well integrity solutions by applying physics-based and data-based models to gauge algorithm performance and robustness. Collaborate with multiple teams to present findings, prototypes, and recommendations to senior management. Perform statistical analysis of field and simulated data to provide reliability insights, confidence levels, and risk assessments. Support business development by evaluating client data for potential improvements in reliability and efficiency. Analyze operational data to create KPIs and develop dashboards that drive action for internal and external clients. Document innovations in intellectual property protection and participate in technical document generation and research publication writing.
Required Qualifications
- Bachelor's or Master's degree in a quantitative discipline (e.g., Mathematics, Statistics, Engineering, Computer Science, Physics, Applied Science) or related discipline with demonstrated research capability
- 3 years of direct work experience in a data related field
- Proficiency in statistical/numerical analysis concepts: regression, linear and multivariate analysis, curve-fitting, sampling methods, descriptive statistics, probability distributions, stochastic models, confidence/risk analysis, optimization
- Experience with statistical/numerical software (e.g., R, Python, MATLAB), database query languages (e.g., SQL), and data science toolkits (e.g., TensorFlow, Keras)
Desired Qualifications
- 5+ years of relevant work experience, including expertise with statistical data analysis
- Proficiency in implementing machine learning and deep learning techniques and algorithms (e.g., KNN, Naïve Bayes, SVM, Decision Forest, RandomForest, Gradient Boosting, CNN) and applying model validation concepts
- Experience in predictive and prescriptive modeling, including model training and validation
- Familiarity with Azure, or other cloud computing services (AWS, Google Cloud, etc.)
- Familiarity with C#, virtual machines / containers
- History of generating technical documents and publications
- Experience in the oil and gas industry, especially operations, and understanding of industry common terminology
Hiring someone like this?
Get your role in front of qualified candidates on Sorce.