Data Scientist / Machine Learning Engineer

Senior Data Scientist / Machine Learning Engineer

Client: U.S. Department of Agriculture (USDA), National Agricultural Statistics Service (NASS)

Program: Sampling Program Enhancement / GENESIS Modernization

Location: Remote (supporting USDA NASS, Washington, DC)

Contract Length: 24 months

Pay Rate: $77.35/hour

Openings: 1

Minimum Experience: 5 years

USDA/NASS Experience: Strongly preferred

SMX Services & Consulting is seeking an experienced Senior Data Scientist / Machine Learning Engineer to support the modernization of GENESIS, USDA NASS's core sampling and survey management platform. This initiative will transition legacy systems to a scalable, cloud-ready, service-oriented architecture that supports advanced analytics, AI, and machine learning capabilities.

About the Role

The selected candidate will develop predictive models, optimize sampling and analytical processes, and build reproducible machine learning workflows integrated with NASS's Lakehouse and cloud ecosystem.

Key Responsibilities

• Develop predictive models to support survey optimization and statistical analysis.
• Perform feature engineering and algorithm tuning.
• Design, train, and optimize supervised machine learning models.
• Validate model performance using A/B testing and other evaluation techniques.
• Build reproducible ML and analytics pipelines.
• Integrate AI/ML solutions within the NASS Lakehouse architecture.
• Implement FAIR data principles (Findable, Accessible, Interoperable, Reusable).
• Apply data governance best practices throughout model development.
• Identify, evaluate, and mitigate model bias.
• Collaborate with developers, architects, statisticians, data specialists, and subject matter experts.
• Document model design, methodology, assumptions, testing, and results.
• Support automated, monitored, and well-documented data pipelines.
• Contribute to testing, validation, and knowledge transfer activities.

Qualifications

• Minimum of 5 years of relevant professional experience.
• Previous USDA or NASS experience is highly desirable.

Required Skills

• 5 years of experience developing and deploying AI/ML solutions.
• Strong proficiency in Python and SQL.
• Experience with one or more major ML frameworks:
• TensorFlow
• PyTorch
• Scikit-learn
• Hands-on experience with:
• Supervised machine learning
• Feature engineering
• Algorithm optimization and tuning
• Model testing and validation
• Reproducible ML pipelines
• Experience with Lakehouse architectures.
• Cloud platform experience, preferably Microsoft Azure.
• Understanding of data governance practices.
• Knowledge of model bias detection and mitigation.
• Experience supporting reproducible analytical environments.

Preferred Qualifications

Experience in one or more of the following areas:

• USDA or USDA NASS programs.
• Federal statistical or data-focused initiatives.
• Federal government technology projects.
• Large-scale survey or sampling systems.
• Azure-based data and AI environments.
• Databricks or similar Lakehouse platforms.
• Statistical workflows using Python, R, and/or SAS.
• Highly regulated or sensitive data environments.

Compensation

• Pay Rate: $77.35/hour
• Contract Duration: 24 months

Security & Eligibility Requirements

• This position supports systems containing sensitive Personally Identifiable Information (PII).
• Candidates must be U.S. Citizens or Lawful Permanent Residents.
• Successful completion of USDA-required fingerprinting and background investigation is required.
• The minimum personnel security requirement is a National Agency Check with Inquiries (NACI), with the possibility of additional investigation or clearance requirements based on position sensitivity.