Senior Decision Intelligence Engineer – NBA

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

📋 Description

• Design, train, and enhance the reinforcement learning policy that powers Humana's Next Best Action platform.

• Create and assess algorithms for decision-making.

• Develop training pipelines.

• Collaborate with data and platform engineering teams.

• Ensure systems comply with clinical eligibility criteria and program-specific goals.

• Engage in all phases of software development, including front-end, back-end, database integration, network and hosting management, user interface, user experience, and server management.

• Identify and troubleshoot failure modes in learned or optimized policies.

• Construct and manage large-scale production systems that serve millions of users.

• Apply reinforcement learning, operations research techniques, or simulation-driven decision systems in a production environment.

• Build extensive ML and data pipelines.

• Monitor experiments, oversee models, and manage artifacts using MLflow.

• Deploy systems that function reliably under production demands.

• Work autonomously on moderately complex to complex technical decisions and impact departmental strategy.

• Attend required training sessions, meetings, or conferences as necessary.

⛳️ Requirements

• Over 5 years of post-undergraduate experience in software engineering or quantitative research focused on building and managing large-scale production systems.

• More than 2 years of post-graduate experience in software engineering or quantitative research related to large-scale production systems.

• At least 2 years of practical experience implementing reinforcement learning, operations research methods, or simulation-driven decision systems in a production setting.

• Familiarity with data-intensive platforms, recommendation systems, optimization engines, or simulation frameworks catering to millions of users.

• Understanding of policy-gradient and value-based reinforcement learning techniques, including PPO, A3C, DQN, and CQL.

• Knowledge of stochastic dynamic programming, discrete-event simulation, or large-scale combinatorial or constrained optimization.

• Deep understanding of Markov Decision Processes, Bellman-equation-based value estimation, reward/objective shaping, exploration-exploitation tradeoffs, and constraint formulation.

• Capability to diagnose policy failure modes, such as instability, ineffective long-horizon credit assignment, and distributional shifts.

• Proficient in Python 3.x.

• Experience with PyTorch or TensorFlow.

• Familiarity with Ray RLlib or similar distributed computation frameworks.

• Experience with Databricks, PySpark, and Delta Lake for large-scale ML or data pipelines.

• Proficient in using MLflow for experiment tracking, model registry, and artifact management.

• Experience delivering reliable production-load systems, beyond research or prototype projects.

• Preferred: experience with multi-agent RL frameworks like PettingZoo.

• Preferred: knowledge of linear programming, mixed-integer programming, Lagrangian relaxation, or constraint programming.

• Preferred: experience in regulated sectors such as healthcare, finance, or insurance.

• Preferred: experience with Gymnasium, SimPy, AnyLogic, or similar simulation frameworks.

• Preferred: familiarity with event-driven feedback loops and retraining or re-optimization processes.

• Preferred: experience with OpenTelemetry instrumentation.

• Capability to provide a high-speed DSL or cable modem for a home office, with a minimum of 25 Mbps download and 10 Mbps upload speeds.

• Satellite and wireless internet services are not permitted.

• A dedicated workspace free from ongoing interruptions to safeguard member PHI/HIPAA information.

🏝️ Benefits

• Bonus incentive plan based on company and/or individual performance.

• Medical benefits.

• Dental benefits.

• Vision benefits.

• 401(k) retirement savings plan.

• Paid time off.

• Company holidays.

• Personal holidays.

• Paid parental leave.

• Paid caregiver leave.

• Short-term disability.

• Long-term disability.

• Life insurance.

• Support for high-speed internet requirements; California home-based associates receive payment for internet expenses.

• Remote work arrangement.

• Occasional travel to Humana offices or Tech Hubs for training or meetings.

• Opportunities for professional development and training.