Staff Software Engineer, ML Inference Compiler & Deployment, Optimus

Tesla is seeking a Staff Software Engineer to join their Autonomy teams, focusing on ML Inference Compiler & Deployment for Optimus, their humanoid robot project. This role is at the intersection of AI, robotics, and autonomous systems, working on one of the world's most advanced AI platforms.

The position involves deep work with Tesla's AI inference stack, which powers both their Autopilot system and Optimus robot. You'll be collaborating with AI Engineers and Hardware Engineers to optimize neural network performance and efficiency. The role is highly impactful, as your work will directly affect millions of Tesla vehicles and the Optimus platform.

This is an exceptional opportunity for someone passionate about cutting-edge AI technology and its real-world applications. You'll work with a purpose-driven inference stack development process, where your optimizations and improvements have immediate, measurable impacts on production systems. The position offers access to Tesla's proprietary MLIR compiler and runtime architecture, allowing for innovative approaches to model optimization.

The role combines deep technical expertise in C++ and Python with specialized knowledge in machine learning compilers and frameworks. You'll be part of a team that's pushing the boundaries of AI hardware and software co-design, working on massively-parallel systems, and contributing to the evolution of autonomous systems and robotics.

Tesla offers comprehensive benefits including competitive salary, equity opportunities, and extensive health coverage. The company's culture promotes innovation, direct impact, and the opportunity to work on technologies that are transforming multiple industries simultaneously.