AI Infrastructure Engineer, Network Deployment & Inference, Optimus

Tesla Tesla · Auto · Palo Alto, CA · Tesla AI

This role focuses on integrating and optimizing ML models for real-time inference within robotic systems, requiring strong C++ and Python programming skills, and experience with embedded systems and performance optimization for neural networks.

What you'd actually do

  1. Integrate ML models into embedded or robotic systems with tight latency and performance constraints
  2. Write Python scripts/tools for training, evaluation, and deployment pipelines
  3. Collaborate with machine learning researchers to bring models from prototype to production
  4. Optimize runtime performance of neural networks on various compute environments (e.g., GPU, CPU, edge accelerators)
  5. Design and implement efficient, robust C++ systems for real-time ML inference and control and for the humanoid robot software stack

Skills

Required

  • Strong programming experience in Python
  • practical experience programming in C/C++ software
  • Solid understanding of machine learning fundamentals (e.g., supervised learning, neural networks, model evaluation)
  • Experience with model inference, deployment, and optimization
  • Experience with embedded systems software design concepts
  • Proficient developing software on a Linux host, for embedded Linux targets (cross-compilation, etc.)

Nice to have

  • Experience with communication standards such as CAN, ethercat and ethernet

What the JD emphasized

  • tight latency and performance constraints
  • real-time ML inference and control

Other signals

  • integrating machine learning models with real-time systems
  • optimize runtime performance of neural networks
  • real-time ML inference and control