Applied RL Engineer

Accountabilities

• Design, implement, and optimize reinforcement learning solutions that address complex operational and strategic challenges.
• Balancing research innovation with production-level engineering standards to deliver scalable and reliable AI systems.
• Develop RL systems that move beyond traditional supervised learning approaches to address dynamic and evolving environments.
• Apply modern reinforcement learning algorithms, simulation techniques, and reward modeling strategies.
• Design and optimize reward functions for challenging, non-trivial environments.
• Build and maintain simulation environments and large-scale data collection pipelines for model training.
• Train neural network-based policies using GPU clusters and scalable infrastructure.
• Evaluate model performance, improve reliability, and support continuous policy optimization after deployment.
• Apply engineering best practices to ensure RL systems are stable, safe, and production-ready.
• Collaborate with research and engineering teams to translate AI concepts into practical solutions.
• Contribute technical insights through documentation, knowledge sharing, research publications, or open-source contributions when applicable.

Requirements

• Deep expertise in reinforcement learning, machine learning engineering, and applied AI development.
• Candidates should demonstrate the ability to combine theoretical knowledge with hands-on experience delivering impactful RL systems.
• Master’s degree or PhD in Computer Science, Machine Learning, Artificial Intelligence, or a related field, or equivalent applied experience.
• 6+ years of combined reinforcement learning research and engineering experience.
• Strong programming skills in Python and experience with modern deep learning frameworks.
• Hands-on experience with reinforcement learning libraries or proprietary RL platforms.
• Strong understanding of probability, optimization, and reinforcement learning theory.
• Experience developing and tuning reward functions in complex environments.
• Experience working with simulation environments and large-scale experience collection systems.
• Experience training deep learning models using GPU-based infrastructure.
• Strong written and verbal communication skills.
• Demonstrated track record of delivering impactful reinforcement learning projects or publishing relevant research.
• Experience with RLHF for large language models is preferred.
• Familiarity with multi-agent reinforcement learning or hierarchical reinforcement learning is a plus.
• Exposure to robotics, control systems, autonomous systems, or related fields is advantageous.
• Contributions to open-source reinforcement learning libraries or environments are valued.

Benefits

• Full-time direct employment opportunity.
• Competitive annual salary range of $100,000-$150,000 depending on experience and qualifications.
• Opportunity to work on advanced artificial intelligence and reinforcement learning initiatives.
• Collaborative environment combining research innovation with real-world engineering applications.
• Career growth opportunities within a technology-focused organization.
• Opportunity to contribute to impactful AI solutions across complex use cases.