Senior Healthcare RL Decision Engineer

Humana Inc; Denver (CO); Remote; 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 at the heart of Humana's Next Best Action platform.

You will own the full RL development lifecycle from feature engineering and reward design through distributed training, evaluation, and production deployment to inform decisions for millions of members. This hands-on, research-oriented role requires implementing RL algorithms, building training pipelines, and ensuring

Qualifications

• 8+ years of software engineering experience building large-scale production systems.
• 3+ years implementing reinforcement learning or deep learning in production.
• Proficiency in Python 3.x; PyTorch or TensorFlow for policy networks.
• Experience with Ray RLlib for distributed RL training.
• Experience with Databricks, PySpark, Delta Lake for large-scale ML pipelines.
• Experience with MLflow for experiment tracking and model registry.

Responsibilities

• Design, implement, and evaluate RL algorithms suited to healthcare decisioning, including policy gradient and offline RL methods.
• Define and maintain member state representation and action space as programs and data sources evolve.
• Instrument training runs with MLflow tracking, rewards, actions, and feature importance for each cycle.
• Own nightly Databricks training workflow: feature engineering, state normalization, distributed training, batch scoring for millions of members.

Skills

Reinforcement learning

Python

PyTorch

TensorFlow

Ray RLlib

Databricks

PySpark

MLflow

Distributed systems

Healthcare domain

Education

Bachelor's degree in computer science or related field

Tools

Ray RLlib

Databricks

PySpark

Delta Lake

MLflow

PyTorch

TensorFlow

Job description

Humana Inc. seeks a Decision Intelligence Engineer to design, train, and continuously improve a reinforcement learning policy at the heart of Humana's Next Best Action platform.

You will own the full RL development lifecycle from feature engineering and reward design through distributed training, evaluation, and production deployment to inform decisions for millions of members. This hands-on, research-oriented role requires implementing RL algorithms, building training pipelines, and ensuring