Lead Decision Intelligence Engineer (Remote) Healthcare RL

Humana Inc; Richmond (VA); Remote; USD 129,000 - 178,000; Full time

Benefits offered by this job

Health benefits

401(k)

Paid time off

Job summary

Humana Inc. seeks a Decision Intelligence Engineer to design, train, and refine reinforcement learning policies for the Next Best Action platform.

You will own the full RL lifecycle, from feature engineering to distributed training and production deployment, ensuring decisions reflect learnable, explainable policies across 8 million member journeys. You will implement RL algorithms, instrument training, and collaborate with data and platform engineers while adhering to clinical eligibility rules

Qualifications

• Bachelor's degree or higher in a related field required.
• 8+ years building and operating large-scale production systems.
• 3+ years hands-on experience with reinforcement learning or deep learning in production.
• Strong understanding of RL concepts and constraints in healthcare.
• Proficiency in Python and ML frameworks.
• Experience with distributed training and ML tooling.

Responsibilities

• Design, implement, and evaluate RL algorithms for healthcare decisioning.
• Define member state representation and action space as programs/data sources evolve.
• Apply reward shaping and constraint mapping in learning objectives.
• Build simulation/backtesting environments and monitor production safety.

Skills

Reinforcement learning

Production ML systems

Policy gradient methods

Exploration-exploitation

Explainability

Education

Bachelor's degree in Computer Science or related field

Tools

Python 3.x

PyTorch

TensorFlow

Ray RLlib

Databricks

MLflow

PySpark

Delta Lake

Kafka

Job description

Humana Inc. seeks a Decision Intelligence Engineer to design, train, and refine reinforcement learning policies for the Next Best Action platform.

You will own the full RL lifecycle, from feature engineering to distributed training and production deployment, ensuring decisions reflect learnable, explainable policies across 8 million member journeys. You will implement RL algorithms, instrument training, and collaborate with data and platform engineers while adhering to clinical eligibility rules