Lead Decision Intelligence Engineer

What you'll do

• Design, implement, and evaluate reinforcement learning algorithms like PPO, DQN, and offline RL methods for healthcare decisioning.
• Define member state representations, action spaces, and reward structures to encode clinical eligibility and program goals.
• Build simulation and backtesting environments to evaluate policy quality and identify failure modes before production deployment.
• Manage the nightly Databricks training workflow including feature engineering with PySpark and distributed training via Ray RLlib.
• Implement constraint mapping to ensure model outputs adhere to hard business rules, such as member caps and cooldown periods.
• Track experiments using MLflow to monitor hyperparameters, reward curves, and action distributions across all training cycles.
• Develop production-quality PySpark jobs to process large-scale data while maintaining clear lineage in the Databricks Unity Catalog.
• Document model behavior and limitations for clinical stakeholders to ensure explainability and compliance with healthcare regulations.

What we're looking for

• Bachelor's degree in computer science or a related field.
• 8+ years of software engineering experience building large-scale production systems like recommendation engines or optimization platforms.
• 3+ years of hands-on experience implementing reinforcement learning or deep learning systems in production.
• Deep familiarity with the Bellman equation, reward shaping, and exploration-exploitation tradeoffs in real-world RL systems.
• Proficiency in Python 3.x with experience using PyTorch or TensorFlow for policy network implementation.
• 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.