Amazon is seeking exceptional talent to help develop the next generation of advanced robotics systems that will transform automation at Amazon’s scale.
We’re building revolutionary robotic systems that combine innovative AI, sophisticated control systems, and advanced mechanical design to create adaptable automation solutions capable of working safely alongside humans in dynamic environments.
This is a unique opportunity to shape the future of robotics and automation at an unprecedented scale, working with world-class teams pushing the boundaries of what’s possible in robotic dexterous manipulation, locomotion, and human-robot interaction.
We are seeking a Senior Software Development Engineer to own the core simulation runtime and physics-engine integration at the heart of our advanced robotics development.
This role focuses on building high-performance, production-grade simulation software — integrating and extending modern physics engines, optimizing contact-rich dynamics for speed and fidelity, and turning simulation research into robust, reusable capabilities.
You will be the engineering owner of how our simulators actually run, working shoulder-to-shoulder with applied scientists to close the simulation-to-reality gap at scale.
Key job responsibilities
- Own the core simulation runtime: integrate, extend, and optimize modern physics engines (e.g., Isaac Lab, MuJoCo, Drake, Newton) for production use
- Engineer high-performance solvers and pipelines for rigid and deformable body dynamics and contact-rich manipulation and locomotion
- Partner with applied scientists to productionize novel simulation methods into robust, maintainable, reusable software
- Optimize simulation performance across CPU/GPU, including profiling, parallelization, and GPU-accelerated compute
- Build and maintain the interfaces, APIs, and model pipelines (e.g., URDF, SDF, USD) that connect simulation to the broader robotics stack
- Develop systematic methods and tooling to measure and reduce the simulation-to-reality gap in collaboration with science and controls teams
- Establish engineering best practices for the simulation codebase — modular architecture, performance-critical C++/Python, testing, and long-term maintainability
- Support large-scale reinforcement learning and policy-training workloads with reliable, reproducible simulation behavior About the team
Our team is building a comprehensive simulation platform for advanced robotics development, combining locomotion and manipulation capabilities.
We operate at the forefront of physics simulation, reinforcement learning, and sim-to-real transfer, collaborating with world-class robotics engineers, applied scientists, and mechanical designers in a fast-paced, innovation-driven environment.