Senior Decision Intelligence Engineer (NBA)

Humana • Work at Home - Kentucky, KY

3d • $106,900 - $147,000 • Hybrid

About The Position

The Senior Decision Intelligence Engineer is a hands-on individual contributor responsible for building, deploying, and operating ML and decisioning pipelines for the NBA Decision Intelligence Platform. This role focuses on production pipeline development, MLOps, feature engineering, scoring workflows, monitoring, and optimization-aware decisioning. You will help ensure the platform selects the right action for the right member while respecting clinical eligibility, suppression rules, channel constraints, program goals, and operational capacity. You will work closely with ML engineers, data engineers, platform engineers, product owners, and decision engine teams to deliver reliable, scalable, and auditable production systems.

Requirements

• 5+ years of experience in machine learning engineering, MLOps, data engineering, platform engineering, optimization engineering, or related software engineering roles.
• Strong hands-on experience with Python, PySpark, SQL, and distributed data processing.
• Experience building and operating production ML pipelines using Databricks, MLflow, Airflow, or equivalent platforms.
• Experience with CI/CD, testing, observability, deployment automation, model monitoring, and production support.
• Experience with cloud-based data platforms such as Databricks, Snowflake, AWS, Azure, or GCP.
• Familiarity with model lifecycle management, experiment tracking, artifact versioning, and release workflows.
• Working knowledge of optimization concepts such as constrained ranking, objective functions, threshold tuning, prioritization, or capacity constraints.
• Ability to translate business rules and operational constraints into reliable production logic.
• Strong troubleshooting skills and ability to operate effectively in complex production environments.
• Clear communication skills and ability to collaborate across technical and non-technical teams.

Nice To Haves

• Experience with personalization, recommendation systems, next-best-action platforms, or decisioning engines.
• Experience with constrained optimization, linear programming, mixed-integer programming, heuristic optimization, or simulation-based evaluation.
• Familiarity with optimization tools such as OR-Tools, SciPy Optimize, PuLP, Pyomo, Gurobi, or equivalent.
• Knowledge of Databricks Lakehouse, Unity Catalog, Delta Lake, Jobs Workflows, and MLflow.
• Experience with Kafka, event-driven pipelines, streaming data, or feedback-loop design.
• Experience in healthcare, insurance, or other regulated environments involving PHI, HIPAA, auditability, and explainability.
• Experience with feature stores, real-time inference, OpenTelemetry, Terraform, or production observability tooling.

Responsibilities

• Build and maintain production pipelines for feature generation, model training, evaluation, scoring, deployment, and monitoring.
• Develop reusable pipeline components using Python, PySpark, Databricks, Delta Lake, and MLflow.
• Support CI/CD, automated validation, model versioning, artifact management, rollback, and release workflows.
• Monitor model performance, data quality, drift, scoring outcomes, and operational health.
• Troubleshoot production issues across feature pipelines, scoring jobs, model artifacts, and downstream integrations.
• Build and maintain member feature pipelines using clinical, behavioral, engagement, operational, web clickstream, and socioeconomic data.
• Ensure features are reproducible, auditable, governed, and performant within the Databricks Lakehouse.
• Operate batch and near-real-time scoring workflows that support personalized outreach across email, SMS, direct mail, digital, and care team channels.
• Integrate model outputs into decisioning platforms, campaign systems, and operational workflows.
• Contribute to optimization logic for next-best-action selection, constrained ranking, member prioritization, and resource allocation.
• Translate business and clinical rules into structured constraints, scoring adjustments, objective functions, and prioritization logic.
• Help balance member relevance, program objectives, outreach limits, channel availability, eligibility rules, suppression periods, and operational capacity.
• Monitor decisioning behavior for scoring anomalies, constraint violations, data issues, and SLA risks.
• Support A/B testing, holdout testing, and measurement workflows for evaluating model and decisioning effectiveness.
• Build automated evaluation gates to prevent underperforming models or scoring workflows from being promoted.
• Validate output quality, action distributions, rule alignment, and downstream decision behavior before production release.
• Document pipeline behavior, assumptions, known limitations, and operational runbooks.
• Support compliance, auditability, explainability, and privacy expectations in a regulated healthcare environment.
• Partner with ML engineering, data engineering, platform, product, rules engine, and decision engine teams.
• Participate in design reviews, code reviews, operational readiness reviews, and production support.
• Communicate implementation tradeoffs, production risks, optimization assumptions, and delivery status clearly.
• Use AI-assisted engineering tools such as GitHub Copilot, Claude, or similar platforms to improve development speed and quality.

Benefits

• medical
• dental
• vision
• 401(k) retirement savings plan
• time off (including paid time off, company and personal holidays, paid parental and caregiver leave)
• short-term and long-term disability
• life insurance

What This Job Offers

• Job Type: Full-time
• Career Level: Senior
• Education Level: No Education Listed