Decision Intelligence Engineer – Next Best Action

This is a fully remote position, open to applicants in United States.

📋 Description

• Design, implement, and assess algorithms tailored for long-horizon, sparse-reward sequential decision-making in the healthcare sector.

• Frame member decision-making challenges as Markov Decision Processes (MDPs) or Partially Observable MDPs.

• Manage the balance between exploration and exploitation suitable for a production healthcare setting.

• Develop simulation and backtesting environments to analyze policy or decision quality prior to production deployment.

• Oversee the nightly Databricks training workflow that involves feature engineering from upstream clinical and operational data sources.

• Implement multi-agent decision-making principles where coordination at the member household or population level is necessary.

⛳️ Requirements

• Over 8 years of experience in software engineering or quantitative research with a focus on building and maintaining large-scale production systems, particularly data-intensive platforms, recommendation systems, optimization engines, or simulation frameworks serving millions of users.

• At least 3 years of practical experience in deploying reinforcement learning, operations research techniques, or simulation-driven decision systems in production environments.

• Relevant expertise includes policy gradient and value-based reinforcement learning (PPO, A3C, DQN, CQL), stochastic dynamic programming, discrete-event simulation, or large-scale combinatorial or constrained optimization.

• Strong understanding of Markov Decision Processes, Bellman-equation-based value estimation, reward or objective shaping, exploration-exploitation tradeoffs, and constraint formulation in practical decision systems.

• Proven ability to identify failure modes in learned or optimized policies, such as instability, poor credit assignment over extended horizons, and distributional shifts across large populations.

• Proficient in Python 3.x; experience with PyTorch or TensorFlow for implementing policy networks or learned models.

• Familiarity with Ray RLlib or similar distributed computation frameworks for large-scale training or optimization.

• Experience with Databricks, PySpark, and Delta Lake for large-scale machine learning or data pipelines processing tens of millions of records.

• Knowledge of MLflow for experiment tracking, model registration, and artifact management.

• Experience in deploying systems that function reliably under production loads, beyond just research or prototype work.

🏝️ Benefits

• Medical, dental, and vision coverage

• 401(k) retirement savings plan

• Paid time off, including company holidays, personal holidays, volunteer time off, and paid parental and caregiver leave

• Short-term and long-term disability insurance

• Life insurance