Lead Data Scientist

Lead Data Scientist

A position is available for a Lead Data Scientist to support large-scale modernization efforts. The role involves serving as a technical leader in applying advanced data science, natural language processing, and statistical methodologies. The objective is to extract, classify, and validate business rules embedded within legacy claims processing systems, enabling the translation of logic into modern, vendor-neutral rule frameworks.

Key Responsibilities

• Apply advanced data science and machine learning techniques to analyze, classify, and interpret business rules from legacy claims processing systems.
• Design, develop, and validate NLP models for automated parsing of legacy code structures.
• Perform latent semantic analysis (LSA), topic modeling, and other text analytics methods on historic documentation.
• Lead the statistical validation of extracted rules to ensure accuracy and alignment with business processes.
• Support the development of a vendor-neutral rules repository by defining data models and ensuring data quality.
• Collaborate with software engineers, legacy system SMEs, and enterprise architects.
• Provide technical leadership on data science best practices, model governance, and deployment pipelines.
• Evaluate new AI/ML technologies to improve throughput, accuracy, and automation.
• Communicate analytical findings and model behavior to technical and non-technical stakeholders.
• Ensure all data science activities comply with federal data standards and security requirements.

Required Qualifications

Education & Experience:

• Minimum of 8 years of experience with a BS/BA degree; or 6 years with an MS/MA; or 3 years with a PhD.
• Must be eligible to obtain and maintain a Public Trust Clearance.
• Demonstrated experience leading large-scale data science, NLP, or machine learning projects in enterprise or federal environments.

Technical Skills:

• Hands-on expertise with NLP techniques including parsing, embeddings, semantic similarity, classification, and information extraction.
• Experience analyzing or modernizing legacy systems (e.g., COBOL, ALC, mainframe environments).
• Proficiency with Python and common data science/ML libraries (e.g., TensorFlow, PyTorch, scikit-learn, spaCy, Hugging Face).

General Skills:

• Strong statistical background, including hypothesis testing and model validation.
• Ability to translate complex analytical findings into clear recommendations.
• Knowledge of agile development methodologies.
• Must be eligible to obtain and maintain a Public Trust level clearance.

Preferred Qualifications:

• Experience supporting modernization efforts within federal healthcare programs.
• Familiarity with Medicare claims processing rules or policy structures.
• Experience building or contributing to knowledge bases or rule repositories.
• Expertise in migrating from mainframe codebases to cloud-native architectures.
• Experience applying AI/ML to large government datasets or in regulated healthcare environments.
• Certifications in data science, AI/ML engineering, or cloud platforms (AWS, Azure, GCP).
• Prior experience leading data science teams or mentoring junior data scientists.
• Active or prior Public Trust Clearance.