Sr. Data Scientist

Join us at SM Energy, where data drives our innovative spirit. As a Senior Data Scientist, you’ll tackle the most exciting analytics challenges, uncover patterns, and craft solutions that revolutionize Petrotechnical problem-solving. Collaborate with experts to enhance decision-making and accelerate value through data. Mentor, innovate, and lead in a role that’s as dynamic as it is impactful.

Ready to shape the future? Apply now and be the change

Essential Roles and Responsibilities

Technical Responsibilities:

• Foundational understanding of the technical and collaborative requirements for full-stack data science and ability to take ownership of projects from proof-of-concept through enterprise model deployment to ensure value delivery

• Proficient ability to wrangle/mine large engineering and geologic datasets and connect data from disparate sources to identify insights, data gaps/quality issues, variable correlations, and patterns using traditional as well as predictive and prescriptive analytics.

• Proficient ability to apply feature engineering skills including normalization, binning, transformation, one-hot encoding, imputing missing data, and feature extraction based on other features.

• Design, develop and evaluate highly innovative models for predictive learning. Leverage machine learning, data mining, statistical techniques, and physics-based models to create new, scalable solutions for business problems.

• Ability to architect and implement various model deployment solutions for on-demand or scheduled batch inferencing as well as real-time optimization and forecasting

• Develop processes, techniques, and tools to analyze and monitor model performance and data drift while ensuring data quality.

• Work closely with data engineers, devops engineers, and front-end developers to create needed databases, datasets, appropriate computing resources, API endpoints, and business facing UIs in support of data ingest, model runtime, and inference output

• Utilize appropriate version control practices to effectively manage codebases and ensure uptime of production deployments

General ML/AI:

• Ability to learn, develop, and successfully apply new technologies in the intersection of data science, statistics, probability, and optimization.

• Be knowledgeable of industry trends and best practices, advising senior management on new and improved data science strategies and techniques that will drive departmental performance leading to improvement in informed decisionmaking, and improving overall business performance.

• Work collaboratively to provide a continuous feedback loop for enterprise data science education and understanding, and support self-service ML skills across the organzation.

• Proficient knowledge of Generative AI concepts and how large language models (LLMs) can be applied to business processes to create new insights

• Understand how edge compute devices can be used to leverage machine learning models in the field and evaluate opportunities for potential edge applications

General Oil and Gas:

• Is competent in own discipline, possessing a thorough working knowledge of data science solutions. Is familiar with the basics of other engineering and geologic specialties and/or disciplines.

• Proficient understanding of key drivers of well performance (geology, well spacing, completion design), hydrocarbon recovery estimation workflows, core analysis, petrophysical evaluations, geologic and seismic data interpretation, reservoir quality evaluation, and industry specific economic analysis

Cybersecurity:

• Data security and data privacy concerns should be known, understood, and properly accounted for.

• Understands security risks regarding use of open source code and publicly available LLMs, and leads education of SM developer community around these concerns

General Knowledge and Skills

Key Competencies: Manages Ambiguity; Cultivates Innovation. Proficient skill in dealing comfortably and effectively with the uncertainty of changes. Handles risk; decides and acts without the total picture. Proficient level skill in being able to make considerable progress and remain calm and composed even when things are uncertain. Deals constructively with problems that do not have clear solutions or outcomes. Works to increase technical knowledge through practical application and knowledge transfer. Moves beyond the traditional ways of thinking; pushes past the status quo and innovates solutions. Finds and champions the best creative ideas and actively moves them into implementation. Introduces new ways of looking at problems and facilitates solutions to addressing those problems. Tries multiple solutions and varied approaches to innovate ideas and create solutions. Fosters environment of continuous improvement and can approach projects with agile methodology. Proficiently manage and engage in multiple initiatives simultaneously and independently prioritize tasks. Apply proficients skills in eliminating potential roadblocks to meet target deadlines. Seek out effective ways to accomplish organizational objectives and goals; align the team’s vision with SM Energy’s strategic vision. Listens effectively to understand the view, concerns, and comments of others while seeking to understand how projects drive value. Critically analyze projects generated by others, integrates additional disciplines as needed, and can identify key elements of a project.

Role Specific Technical Knowledge and Skills

Languages: Proficient skill with Python and its data ecosystem (pandas, numpy, dask, etc.) and ML libraries (scikit-learn, PyCaret, TensorFlow, etc.) is preferred. Similar knowledge of R or MATLAB may be sufficient.

Tools and Skills: Proficient experience analyzing data with SQL. Proficient experience with Jupyter Notebooks, and establishment of virtual coding environments. Working experience utilizing integrated development environments (IDE) such as PyCharm or Visual Studio Code. Proficient applied statistics understanding. Proficient experience and understanding of ML algorithms and ML frameworks. Proficient experience with machine learning operations (MLOps) and version control systems such as Git. Working experience in data visualization using packages such as Matplotlib, Plotly, analytics tools such as Spotfire, Power BI, MATLAB GUI, Tableau, or web development frameworks like Dash, Streamlit etc. Cloud experience, and knowledge of cloud environments, cloud-to-cloud solutions, Azure, DevOps, EDW (Enterprise Data Warehouse) architecture, data virtualization via Denodo, Snowflake cloud data warehouse.

Concepts: Proficient understanding of Statistical and Data Science techniques, including Regression, Classification, Bayesian Methods, Stochastic Methods, ANOVA (analysis of variance), Multivariate Analysis, Neural Networks, Machine Learning, Data Mining and Design of Experiments. Strong math skills (e.g., statistics, algebra). Knowledge of Agile Scrum concepts.

Education: Bachelor's degree in Data Science, Mathematics, Statistics, Analytics, Engineering, Geology,

Computer Science, or related field required. Master’s degree a plus in Data Science,

Analytics, Mathematics, Computer Science, Engineering, Geology, Statistics, or related

discipline. PhD a plus.

Typical Experience: Minimum of 3+ years related experience preferred