Senior Data Scientist — Production ML on Databricks (Azure)

BlueFlag LLC; Pittsburgh (Allegheny County); On-site; USD 140,000 - 190,000; Full time

Benefits offered by this job

Competitive salary

Generous annual leave

Comprehensive health plans

401(k) with match

Life insurance

Professional development

Job summary

BlueFlag LLC is seeking a Senior Data Scientist to support a premier data and AI platform for the Department of Veterans Affairs. You will work directly with internal clients to turn operational problems into production machine learning and AI solutions on Databricks in Azure, and help their teams adopt modern cloud tooling.

This role is hands-on, taking models from notebook to production and keeping them running.

Qualifications

• Bachelor's degree in Engineering, CS, Stats, Math, Systems or related field and 15+ years experience (or commensurate).
• Proficient in Python (pandas, NumPy, SciPy, scikit-learn) and advanced SQL for data analysis.
• 2+ years hands-on with a leading cloud data platform such as Databricks, Azure, AWS, or GCP.
• Experience end-to-end data science workflow, experiment tracking, and model management with MLflow.
• Strong ML foundation: supervised/unsupervised methods, gradient boosting, tuning, and evaluation.
• Experience with Spark/PySpark and large datasets; ability to explain model behavior.
• Familiarity with LLMs, RAG, and agentic AI workflows; governance and bias awareness.
• VA/federal healthcare data familiarity and PHI/PII handling; federal privacy/security practices.
• Mastery in communicating complex results to non-technical stakeholders.

Responsibilities

• Consult with internal clients to frame problems, define success metrics, and scope.
• Build data products and workflows from discovery to production deployment.
• Migrate workloads to Python and Databricks, achieving runtime/cost gains.
• Develop, train, and validate ML models for complex business problems.
• Engineer features and reusable pipelines on large datasets with PySpark/SQL.
• Track experiments, register models, and manage versions with MLflow.
• Deploy models for batch and real-time serving; automate retraining with CI/CD.
• Monitor models in production for drift, quality, and alert thresholds.
• Lead AI adoption with RAG, document summarization, and classification use cases.
• Evaluate LLM outputs for accuracy and safety; document governance decisions.
• Create reference use cases with tutorials and training to drive cloud tooling adoption.
• Host office hours with client analysts to upskill teams; present findings to leadership.

Skills

Python

SQL

Databricks

PySpark

ML

Git

Cloud platforms

MLflow

Communication

Education

Bachelor's degree (Engineering/CS/Stats/Math)

Master's or PhD in quantitative field

Tools

Databricks

Azure

Power BI

Unity Catalog

Delta Lake

Job description

BlueFlag LLC is seeking a Senior Data Scientist to support a premier data and AI platform for the Department of Veterans Affairs. You will work directly with internal clients to turn operational problems into production machine learning and AI solutions on Databricks in Azure, and help their teams adopt modern cloud tooling.

This role is hands-on, taking models from notebook to production and keeping them running.