Senior Reinforcement Learning Engineer

Company: Halian | Managed Services, Recruitment Agency &
Location: Miami
Posted on: January 9, 2026

Job Description:

Job Description Senior Reinforcement Learning Engineer – Bio-Defense & Complex Systems - (US-based only) We’re seeking a Senior Reinforcement Learning Engineer to join an advanced AI-driven technology company solving high-impact, real-world problems in healthcare, insurance, and complex system modeling. This role focuses on designing, implementing, and deploying RL-based decision-making and adaptive control systems in critical bio-defense, claims resilience, and risk-sensitive environments. Role Overview: As a Senior RL Engineer, you’ll work at the intersection of reinforcement learning, simulation, and applied machine learning. You will translate theoretical RL and systems models into operational, production-ready solutions with measurable real-world impact. This is a hands-on role, with autonomy to drive experimentation, training, validation, and deployment of RL and multi-agent systems. Key Responsibilities: Design, implement, and optimize RL agents for complex, dynamic, and high-stakes environments Develop simulation environments (stochastic, agent-based, or hybrid) to train and evaluate RL policies Integrate RL models with supervised and unsupervised ML pipelines using structured (tabular) and temporal data Evaluate model robustness, generalization, and failure modes under uncertainty or adversarial conditions Collaborate with domain experts to formalize reward functions, constraints, and state spaces Maintain hands-on involvement in experimentation, deployment, and optimization Required Qualifications: 4 years of ML experience, with deep expertise in reinforcement learning Strong foundation in MDPs, POMDPs, policy gradients, value-based methods, and model-based RL Hands-on experience with RL frameworks such as Stable-Baselines, RLlib, or PyTorch/JAX implementations Strong Python skills and experience building end-to-end ML pipelines Comfortable working with tabular, time-series, and simulation-generated data Preferred / Nice to Have: Experience with agent-based modeling, digital twins, or hierarchical/multi-agent RL Experience in high-stakes, regulated, or mission-critical environments Familiarity with uncertainty modeling, robustness testing, or safety-aware RL What We Value: Systems-first mindset: thinking beyond models to real-world operational impact Ability to work in ambiguous problem spaces with incomplete data Strong ownership, technical rigor, and ethical awareness in high-impact AI systems Why Join: Work on mission-critical AI challenges that directly influence real-world outcomes High autonomy and deep technical ownership Shape next-generation decision-making and adaptive AI systems Location: Florida/Remote within the US only available. If you’re passionate about reinforcement learning, simulation, and building AI systems with tangible, high-stakes impact, this is an exciting opportunity to make a real difference.

Keywords: Halian | Managed Services, Recruitment Agency &, Jupiter , Senior Reinforcement Learning Engineer, IT / Software / Systems , Miami, Florida