Applied RL Engineer

Role Overview

Design, develop, and deploy advanced reinforcement learning (RL) systems to solve complex decision-making and operational challenges. Blend cutting-edge research with production-grade engineering to take RL solutions from experimentation into reliable deployment.

Responsibilities

• Design, implement, and optimize RL solutions for complex strategic/operational problems
• Train, evaluate, and deploy RL models for dynamic decision-making environments
• Use modern RL methods beyond supervised learning for evolving environments
• Apply RL algorithms, simulation, and reward modeling strategies
• Design and tune reward functions for challenging environments
• Build and maintain simulation environments and large-scale data collection pipelines
• Train neural network policies using GPU clusters and scalable infrastructure
• Evaluate reliability and performance; support continuous policy optimization after deployment
• Apply engineering best practices to make RL systems stable, safe, and production-ready
• Collaborate with research and engineering teams; document and share technical insights
• Contribute via publications or open-source when applicable

Requirements

• Deep expertise in reinforcement learning and machine learning engineering
• Master’s degree or PhD in CS/ML/AI (or equivalent applied experience)
• 6+ years combined RL research and engineering experience
• Strong Python programming skills
• Experience with modern deep learning frameworks
• Hands-on experience with RL libraries or proprietary RL platforms
• Strong foundation in probability, optimization, and RL theory
• Experience tuning reward functions in complex environments
• Experience with simulation and large-scale experience collection systems
• Experience training deep learning on GPU-based infrastructure
• Strong written and verbal communication skills
• Track record delivering impactful RL projects and/or publishing relevant research

Nice to Have

• RLHF experience for large language models
• Multi-agent RL or hierarchical RL
• Experience with robotics, control systems, or autonomous systems
• Contributions to open-source RL libraries or environments

Remote / Location

• Fully remote within the United States