Senior Robotics Reinforcement Learning Engineer

About Technology Innovation Institute

Technology Innovation Institute (TII) is a publicly funded research institute located in Abu Dhabi, UAE. It hosts a diverse group of top scientists, engineers, mathematicians, and researchers worldwide who transform challenges into cutting-edge research and prototype technologies that advance society.

Position Overview

This senior role within TII's Robotics Research Center focuses on developing and deploying advanced Reinforcement Learning (RL) solutions specifically tailored for robotics, drone swarms, and autonomous systems. The incumbent will create novel RL architectures, apply state-of-the-art techniques, and build scalable distributed control systems.

Key Responsibilities

• Design, develop, and optimize RL algorithms for robotic platforms, unmanned aerial vehicle (UAV) swarms, and autonomous agents, supporting long-term planning and strategic decision making.
• Create and assess multi-agent reinforcement learning (MARL) frameworks to facilitate coordination, collision avoidance, and cooperative decisions among multiple drones.
• Implement efficient training workflows for large-scale RL simulations, enhancing performance and ensuring effective simulation-to-real-world transfer for robotic and aerial applications.
• Continuously update knowledge on cutting-edge RL research; explore hybrid learning methods such as neurosymbolic approaches and combinations of model-based and model-free learning.

Core Competencies & Skills

• Strong mastery of reinforcement learning techniques including policy-gradient methods, Q-learning, actor-critic architectures, and hierarchical RL.
• Experience with MARL, federated learning models, control systems (both centralized and decentralized), and policies enhanced by memory mechanisms.
• Familiarity with sim-to-real transfer strategies, domain randomization, and transfer learning within robotics contexts.
• Proficiency using RL toolkits such as Ray RLlib, Stable Baselines3, and others.
• Hands-on experience with simulation tools including PyBullet, Isaac Gym, Gazebo, MuJoCo, and AirSim.
• Familiarity with AI development platforms like PyTorch, TensorFlow, and JAX.
• Programming expertise primarily in Python for research and prototyping, alongside C++ for high-performance segments, middleware (e.g., ROS2), and real-time robotic control.
• Experience with containerization (Docker), distributed training environments, GPU cluster management, CUDA programming, and large-scale simulation workflows.
• Deployment experience of RL models in robotic middleware such as ROS2, PX4, and MAVSDK.

Qualifications

• Master’s degree or PhD in Computer Science, Robotics, Artificial Intelligence, Machine Learning, or a closely related area.
• Demonstrated history implementing RL algorithms in robotic or UAV environments.
• Deep knowledge of multi-agent systems, swarm robotics, and practical control systems.
• Experience bridging the gap between simulations and real-world system deployments.
• Strong analytical problem-solving skills coupled with a research-focused mindset.

Preferred Qualifications

• Experience with safety-critical or constrained reinforcement learning systems.
• Background in distributed optimization, graph learning, or networked system structures.
• Open-source contributions to RL or robotics toolsets.
• Authorship of publications in AI or robotics conferences.

About TII’s Research Approach

TII emphasizes overcoming significant societal challenges through rigorous scientific discovery, advanced facilities, and collaboration with global leading institutions. The institute fosters groundbreaking advancements across AI, autonomous robotics, quantum computing, secure systems, and more.