Senior AI/ML Data Scientist with advanced analytics experience

Job Summary

InnoVet Health is seeking a Senior AI/ML Data Scientist to support national AI initiatives across federal healthcare, with a primary focus on the Department of Veterans Affairs. This is a full‑performance‑level role: candidates must arrive with the technical judgment, operational maturity, and self‑sufficiency to contribute immediately within federal environments.

You will design and evaluate machine learning and LLM‑based solutions, build reproducible pipelines, assess data quality in complex health datasets, and translate analytical findings into actionable insights that improve Veteran care and reduce provider burden. Work includes AI governance, model evaluation, explainability, and continuous monitoring, ensuring all solutions are safe, trustworthy, and aligned with federal priorities and standards.

This role offers remote flexibility, competitive benefits, and the opportunity to shape the future of responsible AI in federal healthcare.

Responsibilities

AI/ML Development & Evaluation

• Design and implement end‑to‑end ML pipelines, including ingestion, preprocessing, feature engineering, model selection, training, evaluation, and deployment, with clear rationale for design choices and tradeoffs.
• Conduct structured evaluations of LLM‑based and agentic AI approaches, including safety, hallucination, robustness, and workflow fit for federal healthcare use cases.
• Apply statistical and machine learning methods in Python and SQL to analyze large healthcare datasets and support use case validation.
• Develop reproducible analyses using version control (git) and experiment‑tracking tools (primarily MLflow).

Data Quality, Readiness & Health Data Expertise

• Audit and assess incoming health data (EHR, claims, operational datasets) for missingness, inconsistency, structural irregularities, and bias; document principled decisions about data handling.
• Collaborate with data engineering and source system owners to improve upstream data quality, metadata, and data readiness for AI/ML workloads.
• Work within secure government cloud environments (AWS GovCloud, Azure Government) and distributed compute platforms (Databricks, Spark).

AI Governance, Safety & Compliance

• Contribute to federal AI governance activities, including model documentation, risk assessments, and participation in internal review or oversight processes.
• Design evaluation plans that support continuous monitoring, drift detection, and re‑validation of AI systems in production.
• Ensure all work aligns with principles of explainability, fairness, privacy, and emerging federal AI policy, standards, and responsible‑AI guidance.

Stakeholder Engagement & Workflow Integration

• Work with VA stakeholders to gather and refine requirements for advanced analytics and AI initiatives.
• Translate analytical and modeling outputs into clear, accurate visualizations and narratives tailored to technical, clinical, and executive audiences.
• Ensure AI solutions integrate into existing clinical and operational workflows, minimizing burden and maximizing adoption.
• Manage multiple concurrent projects across VA and other federal health clients, balancing deep technical work with stakeholder engagement and deliverable timelines.

Deliverables & Federal Contract Execution

• Prepare formal federal deliverables including technical memos, evaluation reports, model cards, data management plans, and reproducibility documentation.
• Develop clear, defensible analyses suitable for audit, external review, and transition into federal environments.

Qualifications

Required

• Master’s degree in Data Science, Statistics, Computer Science, or a related quantitative field.
• 5+ years of hands‑on experience in applied data science or machine learning, with a demonstrated track record of delivering work in real‑world, production, or contract environments.
• Proficiency in Python (primary language for all data science work) and SQL fluency, including comfort with T‑SQL and Databricks environments; R is a valued secondary skill for candidates from research or biostatistics backgrounds.
• Experience analyzing large and complex datasets. Experience with healthcare data, especially VA healthcare data, is preferred but not required.
• Familiarity with distributed computing platforms (e.g., Databricks, Spark) and secure government cloud environments (AWS GovCloud, Azure Government), or equivalent experience with commercial cloud systems (e.g., AWS, Azure, GCP) preferred.
• Familiarity with established data science and ML lifecycle frameworks (e.g., CRISP‑DM OSEMN, TDSP) and the ability to structure work using industry‑standard processes, documentation practices, and governance checkpoints.
• Exposure to large language models (LLMs) and agentic AI approaches, with the ability to evaluate potential use cases and limitations.
• Ability to clearly interpret and present results to both technical and non‑technical audiences.
• Ability to obtain and maintain VA suitability and a federal PIV badge.
• U.S. Citizen or Green Card holder.
• No 1099, corp‑to‑corp, or international outsourcing.

Preferred

• Direct experience working within the Department of Veterans Affairs on data science or adjacent projects.
• Broader healthcare data science experience across EHR, claims, imaging, or clinical NLP.
• Federal consulting experience and familiarity with government deliverables and FedRAMP environments.
• ML engineering capabilities (model versioning, monitoring, CI/CD, containerization).

Job Type: Full-time

Pay: From $140,000.00 per year

Benefits:

• 401(k)
• 401(k) matching
• Dental insurance
• Health insurance
• Paid time off
• Referral program
• Vision insurance

Application Question(s):

• This position works with government contracts. Under Order 11935, either U.S. Citizenship or valid permanent residency is required. Answer 2 if you are a US citizen, 1 if you have a permanent resident card.
• Please provide the link to your LinkedIn account.
• Please provide the link to your GitHub account.
• How many years of experience do you have working on federal contracts?

Education:

• Bachelor's (Required)

Experience:

• Python: 5 years (Required)
• T-SQL: 3 years (Required)
• Agentic AI : 3 years (Required)
• Large Language Models: 3 years (Required)
• healthcare data : 3 years (Required)

Work Location: Remote