Lead Decision Intelligence Engineer — Next Best Action

Humana Inc; Frankfort (KY); Hybrid; USD 129,000 - 178,000; Full time

Job summary

Humana Inc. seeks a Decision Intelligence Engineer to design, train, and continuously improve a reinforcement learning policy for the Next Best Action platform serving millions of members.

You will own the full RL lifecycle from feature engineering to production deployment, ensuring decisions are informed by a learning policy that improves with every interaction. The role is hands-on and research-oriented, requiring collaboration with data, platform engineers, and governance teams to align with

Qualifications

• Bachelor's degree in computer science or related field.
• 8+ years of software engineering experience building and operating large-scale production systems.
• 3+ years of hands‑on experience implementing reinforcement learning or deep learning systems in production.
• Deep familiarity with the Bellman equation, reward shaping, exploration-exploitation tradeoffs, and constraint mapping.
• Demonstrated ability to diagnose RL-specific failure modes in real-world systems.
• Proficiency in Python 3.x; experience with PyTorch or TensorFlow.
• Experience with Ray RLlib for distributed RL training at scale.
• Experience with Databricks, PySpark, and Delta Lake for large-scale ML pipelines.
• Experience with MLflow for experiment tracking, model registry, and artifact management.
• Track record of shipping ML systems that operate reliably under production load.

Responsibilities

• Design, implement, and evaluate RL algorithms suited to healthcare decisioning.
• Define and maintain member state representation and action space.
• Apply Bellman equation and reward shaping to encode eligibility and objectives.
• Manage exploration-exploitation tradeoffs in production.
• Build simulation and backtesting environments for policy evaluation.
• Diagnose and remediate RL failure modes and distributional shift.
• Define reward thresholds and automated evaluation gates in training workflows.
• Instrument training runs with MLflow tracking of hyperparameters and metrics.
• Own nightly Databricks training workflow and feature engineering pipelines.
• Collaborate with Data Eng to ensure correct training inputs and auditable pipelines.
• Write production-quality PySpark feature engineering jobs; manage model artifacts and lifecycle in MLflow.
• Apply multi-agent RL concepts and enforce constraint-aware objectives.
• Collaborate with Rules Engine to align RL priorities with eligibility guards.
• Document model behavior and support explainability for stakeholders.

Skills

Software engineering

Reinforcement learning

Python

PyTorch or TensorFlow

Ray RLlib

Databricks/PySpark

MLflow

Distributed training

Explainability

Education

Bachelor's degree in computer science

Tools

Databricks

PySpark

Delta Lake

MLflow

Ray RLlib

Kafka

Redis

Gymnasium

Job description

Humana Inc. seeks a Decision Intelligence Engineer to design, train, and continuously improve a reinforcement learning policy for the Next Best Action platform serving millions of members.

You will own the full RL lifecycle from feature engineering to production deployment, ensuring decisions are informed by a learning policy that improves with every interaction. The role is hands-on and research-oriented, requiring collaboration with data, platform engineers, and governance teams to align with