Reinforcement Learning (RL) Engineer

The company is a publicly funded research institute based in Abu Dhabi, United Arab Emirates. It is home to a diverse community of leading scientists, engineers, mathematicians, and researchers from across the globe, transforming problems and roadblocks into pioneering research and technology prototypes that help move society forward.

This role is part of the company’s Robotics Research Center. We are seeking a talented Reinforcement Learning Engineer with expertise in developing and deploying RL solutions for robotics, swarm intelligence, and drone systems. The ideal candidate will have a strong foundation in both the theoretical RL and the practical implementation of algorithms in real-world environments. You will design novel RL architectures, integrate advanced methodologies, and build scalable systems capable of handling complex distributed control problems.

Key Responsibilities:

• RL Algorithm Development & Integration: Design, implement, and optimize RL algorithms for robotic platforms, UAV swarms, and autonomous agents. Integrate and implement RL solutions for long-horizon planning and decision-making.
• Multi-Agent Reinforcement Learning (MARL): Build and evaluate MARL frameworks for coordination, deconfliction, and cooperative decision-making in multi-drone systems.
• Engineering & Deployment: Implement efficient training pipelines for large-scale RL simulations, optimize performance in simulation-to-real transfer for robotics and aerial vehicles.
• Research & Innovation: Stay up to date with state-of-the-art RL methodologies. Investigate hybrid learning paradigms (e.g., neurosymbolic methods, model-based/model-free hybrids).

Core Competencies:

• Reinforcement Learning Expertise: Strong understanding of policy-gradient methods, Q-learning, actor-critic frameworks, and hierarchical RL. Hands-on experience with MARL, federated learning, centralized vs decentralized control, and memory-augmented policies.
• Development Tools & Libraries: Familiarity with RL frameworks such as Ray RLlib and Stable Baselines3. Experience with simulation environments like PyBullet, Isaac Gym, Gazebo, MuJoCo, and AirSim. Proficient in AI frameworks including PyTorch, TensorFlow, and JAX.
• Programming Skills: Python is the primary language for RL research, prototyping, and experimentation; C++ for performance-critical components and real-time control.
• Systems & Infrastructure: Proficient with Docker, distributed training systems, and GPU clusters; familiarity with CUDA and large-scale simulation pipelines; experience deploying RL models in robotics middleware (ROS2, PX4, MAVSDK).

Qualifications:

• Master’s or PhD in Computer Science, Robotics, AI/ML, or a related field.
• Proven track record of implementing RL algorithms for robotics or UAV applications.
• Strong expertise in multi-agent systems, swarm robotics, and real-world control.
• Experience bridging simulation and real-world deployment.
• Excellent problem-solving ability and research-driven mindset.

Preferred Qualifications:

• Experience with safety-aware or constrained RL for critical systems.
• Background in distributed optimization, graph-based learning, or networked systems.
• Contributions to open-source RL or robotics frameworks.
• Publications in AI/robotics conferences.

At the company, we help society overcome its biggest challenges through rigorous scientific discovery and inquiry, leveraging state-of-the-art facilities and collaboration with leading international institutions. Our approach fosters new and disruptive breakthroughs in AI, advanced materials, autonomous robotics, cryptography, digital security, directed energy, quantum computing, and secure systems.