Senior Robotics Engineer

About the Role

We’re looking for an experienced engineer passionate about creating the next generation of autonomous and intelligent robotic systems. In this position, you’ll lead the development of learning-driven control architectures that enable robots, drones, and distributed agent systems to make complex, adaptive decisions in real-world environments. You’ll collaborate across hardware, software, and AI research teams to turn theoretical reinforcement learning concepts into practical robotic intelligence that scales.

Primary Focus Areas

1. Learning System Design & Implementation
   Develop, optimize, and validate reinforcement learning algorithms for robotic control, decision-making, and motion planning. Architect modular learning pipelines that perform reliably across simulation and real-world deployment.
2. Cooperative & Multi-Agent Control
   Design and evaluate intelligent coordination strategies for multi-robot and UAV systems, enabling communication, resource sharing, and joint decision-making within distributed environments.
3. Simulation & Real-World Integration
   Create scalable training ecosystems, accelerate experimentation using high-performance compute, and guide the transfer of trained behaviors from virtual environments to physical robotic platforms.
4. Research & Exploration
   Contribute to the evolution of adaptive robotics through exploration of hybrid models—combining model-based reasoning, deep reinforcement learning, and symbolic planning.

Technical Expertise

Deep knowledge of reinforcement learning principles including policy optimization, actor–critic algorithms, and hierarchical or goal-conditioned learning.
Proven ability to apply multi-agent RL for collaboration, competition, and distributed problem-solving.
Experience bridging simulation and real deployment, using techniques like domain adaptation, transfer learning, and system randomization.
Familiarity with robotics middleware (e.g., ROS2, PX4, MAVSDK) and real-time control integration.

Toolset & Environments

Proficiency in Python for research and experimentation, and C++ for low-latency, embedded, or middleware components.
Experience with frameworks such as PyTorch, Ray RLlib, or Stable Baselines for training and deployment.
Skilled with simulation environments like Isaac Gym, Gazebo, MuJoCo, or AirSim.
Working knowledge of Docker, GPU-based compute, and distributed training environments.

What You Bring

Advanced degree (Master’s or PhD) in Robotics, Computer Science, AI, or a related field.
Demonstrated experience developing and deploying RL solutions for robotic or aerial systems.
Strong understanding of control systems, perception-driven behaviors, and multi-agent communication.
Ability to collaborate in cross-disciplinary research and engineering teams.

Bonus Experience

Background in safe or constrained learning, adaptive control, or graph-based intelligence.
Experience contributing to open-source robotics or AI projects.
Publications or patents in areas related to learning-based robotics or autonomy