AI Inference Engineer - Model Optimization & Deployment

We are looking for an AI Inference Engineer to optimize large-scale models for production-ready deployment on edge devices. The engineer will focus on compressing, accelerating, and deploying complex models for power- and thermal-constrained vehicle SOCs.

Requirements

• Optimize large-scale models using advanced quantization and mixed-precision inference workflows
• Write custom CUDA kernels and TensorRT Plugins for maximum memory bandwidth and minimized latency
• Write production-level C++ and Python code for real-time inference on vehicle SOCs
• Perform rigorous parity checking and accuracy recovery between PyTorch frameworks and compiled edge binaries

Benefits

• Paid time off
• Unpaid time off
• Health insurance
• Long-term care insurance
• Long-term and short-term disability insurance
• Life insurance
• Zoox Stock Appreciation Rights
• Amazon RSUs