<strong>Reinforcement Learning Engineer – Remote</strong><br><br><a href="https://himalayas.app/companies/bright-vision-technologies">Bright Vision Technologies</a> is a technology consulting and software development company delivering cloud, AI, data, and enterprise solutions across the United States.<br>This is a fantastic opportunity to join an established and well-respected organization offering tremendous career growth potential.<br><br><strong>Job Title: </strong>Reinforcement Learning Engineer<br><strong>Location: </strong>100% Remote (U.S.)<br><strong>Position Type: </strong>Full-time, Direct W2<br><strong>Salary Range: </strong>$100,000–$150,000 Annually<br><strong>Experience Required: </strong>6+ years<br><br><strong>Sponsorship: </strong>U.S. Citizens, Green Card Holders, EAD Holders, and H-1B transfer candidates are encouraged to apply. We are unable to sponsor new H-1B visa petitions for this position.<br><br><strong>Job Summary</strong><br>We are looking for a Reinforcement Learning Engineer to design, train, and deploy RL-based systems for high-impact decision-making problems where supervised learning alone is insufficient. The role requires deep familiarity with modern reinforcement learning algorithms, simulation environments, reward modeling, and the engineering complexity of training and evaluating policies at scale. The ideal candidate has both research depth and engineering pragmatism, with experience taking RL solutions out of the lab and into production where stability, safety, and ongoing improvement are critical.<br><br><strong>Key Responsibilities</strong><ul><li>Design and implement reinforcement learning solutions for sequential decision-making problems in real and simulated environments.</li><li>Develop, calibrate, and maintain simulation environments suitable for large-scale agent training.</li><li>Implement and evaluate modern RL algorithms including policy gradient, actor-critic, off-policy, and offline RL methods.</li><li>Engineer reward functions and shaping strategies that align agent behavior with desired outcomes and safety constraints.</li><li>Apply offline RL and imitation learning techniques where exploration is costly or unsafe.</li><li>Use RLHF, DPO, and related techniques for fine-tuning large language models when relevant.</li><li>Build scalable training infrastructure for distributed RL, including efficient experience collection and replay systems.</li><li>Optimize training stability and sample efficiency through algorithmic and engineering improvements.</li><li>Design rigorous evaluation protocols, including out-of-distribution and adversarial test cases.</li><li>Implement safety mechanisms such as constraint enforcement, conservative policies, and human-in-the-loop oversight.</li><li>Collaborate with applied scientists and product teams to identify high-value RL use cases.</li><li>Monitor deployed policies and models in production for drift, regression, and unintended behaviors, building the alerting