Data Scientist

What Youll Do

A career at Pantex can offer you the opportunity to make a personal impact on our nation. We recognize that excellent employees are absolutely critical for mission success. We are seeking an advanced Data Scientist to develop validate and deploy statistical models and machine learning algorithms that drive mission-critical insights operational efficiency and advanced forecasting capabilities.

Primary duties include applying statistical methods and machine learning principles to analyze complex datasets build predictive and prescriptive models for operational improvement and translate high-value business problems into tangible data-driven solutions.

Additional duties may include conducting advanced research into new Artificial Intelligence (AI)/Machine Learning (ML) techniques collaborating with Data Engineers and Machine Learning Operatons (MLOps) teams to deploy models and presenting complex analytical findings to technical and non-technical stakeholders.

Core Responsibilities and Duties

• Design implement and validate Machine Learning and statistical models for high-impact use cases including predictive maintenance systems resource optimization algorithms and advanced forecasting.
• Design and manage the MLOps process for models including containerization automated testing and deployment using MLOps platforms and Continuous Integration (CI)/Continuous Deployment (CD) pipelines to transition models from development to a secure live environment.
• Maintain and monitor deployed models in production rapidly diagnosing and resolving issues managing data drift and model drift and retraining models to ensure sustained performance and reliability.
• Utilize advanced statistical and algorithmic techniques to perform comprehensive data analysis identify trends anomalies and critical patterns in large complex operational safety and financial datasets.
• Partner with business units to define problem statements gather data requirements and ensure the successful integration and adoption of models into existing enterprise processes.
• Develop and maintain robust production-ready code for model training feature engineering pipelines and validation routines ensuring model reproducibility and scalability.
• Ensure all models data usage and code comply with National Nuclear Security Administration (NNSA) security standards data governance policies and ethical AI principles.

Other Responsibilities and Duties

• Evaluate and recommend the strategic use of emerging AI technologies such as Large Language Models (LLMs) and Generative AI for both mission and internal support applications.
• Collaborate closely with Data Engineers and Data Architects to prepare data infrastructure and define necessary feature stores for efficient model development and training.
• Create comprehensive technical and non-technical documentation detailing model architecture methodology performance results and business impact.

What You Can Expect

• Meaningful work and unique opportunities to support missions vital to national and global security.
• Top-notch dedicated colleagues.
• Generous pay and benefits with a stable organization.
• Work-life balance fostered through flexible work options and wellness initiatives.

Minimum Job Requirements

• Bachelors degree (BS) in engineering/science discipline: Minimum 2 years of relevant engineering/science experience ranging from 3 to 7 years.
• OR Applicants without a bachelors degree may be considered based on a combination of at least 10 years of completed education and/or relevant experience

Department of Energy (DOE) Order 426.2A Requirements

• Not Applicable

Preferred Job Requirements

• At least 1 year focused on applying data science techniques machine learning and managing model deployment in a production setting.
• Proficiency in statistical programming languages such as Python or R and experience in relevant machine learning libraries (e.g. scikit-learn PyTorch TensorFlow).
• Demonstrated experience with MLOps principles including model versioning containerization (e.g. Docker) and deployment via cloud platforms.
• Demonstrated experience with Structured Query Language (SQL) and querying relational databases as well as handling large complex and unstructured datasets.
• The ability to obtain and maintain a Department of Energy Q clearance is required.
• Masters degree (MS) or Ph.D. in a quantitative field with minimum 3 years of relevant experience.
• Expert proficiency in statistical programming languages such as Python or R and deep expertise in relevant machine learning libraries (e.g. scikit-learn PyTorch TensorFlow).
• Experience with cloud-based MLOps platforms (e.g. Datarobot Azure ML AWS SageMaker) and CI/CD tools for automated model pipelines.
• Prior domain experience in industrial optimization predictive maintenance or complex resource forecasting.
• Knowledge of big data technologies such as Spark and familiarity with collaborative coding environments and version control (Git).