AI Infrastructure Engineer, Model Optimization & Deployment, Optimus - Palo Alto [247659]

$176,000 - $420,000 yearly

Job Description

Tesla AI is solving robust, real-world AI through humanoid robots. As a Software Engineer for the Optimus team, you will build the tools and infrastructure to make and measure improvements to neural network architecture, visualize data, assist with exporting and deploying neural networks to Tesla’s neural network chip with real-time latency constraints on Optimus, and evaluate experimental results. You will help us automate the entire workflows of training, validation, and production of Optimus. Most importantly, you will see your work repeatedly shipped to and utilized by thousands of Humanoid Robots in real world applications.

The Role

  • Optimize ML models for latency, memory usage, and inference speed
  • Quantize, prune, and convert models (e.g., to ONNX, TensorRT, TFLite) for deployment on various platforms (cloud, edge, mobile)
  • Benchmark and profile model performance across different environments
  • Package and deploy models as REST APIs, batch jobs, or streaming services using tools like FastAPI, Flask, or gRPC
  • Implement CI/CD pipelines for automated testing and deployment of ML models
  • Ensure scalability and reliability of ML services in production environments

Requirements

  • Strong proficiency in Python and PyTorch
  • Experience with model optimization tools (e.g., ONNX, TensorRT, TFLite, TVM)
  • Experience with model inference optimization and quantization
  • Solid understanding of containerization and orchestration (Docker, Kubernetes)
  • Familiarity with cloud platforms (AWS, GCP, Azure) and serverless deployments
  • Strong grasp of software engineering principles and CI/CD pipelines
  • Experience deploying models to edge devices or mobile platforms
  • Knowledge of data serialization formats (e.g., protobuf, Avro)
  • Exposure to observability tools (e.g., Prometheus, Grafana) for ML monitoring
Anthony Antonucci

Qualifications

Relevant experience in Tesla AI; strong problem-solving skills; commitment to Tesla mission.

Immediate Fill

No