Perception Deployment Engineer - Model Deployment & Optimization

📋 Description

• Design and develop production-level, low latency, and memory-safe C++ and CUDA code for real-time
• Optimize large-scale models (Multi-Modal Sensor Fusion models, LLMs, VLMs) using advanced
• Architect and implement model conversion and compilation pipelines using TensorRT for edge
• Perform rigorous parity checking, accuracy recovery, and latency benchmarking between PyTorch
• Develop and optimize custom ML OPs and TensorRT Plugins with efficient CUDA kernels to minimize

🎯 Requirements

• Production-level C++ (14/17/20) and Python programming skills, with experience developing
• Deep expertise in model compression technologies (e.g., model quantization such as PTQ and QAT) and
• Proven experience optimizing large-scale models (Multi-Modal Sensor Fusion models, LLMs, VLMs/VLAs)
• Extensive experience with model conversion/compilation pipelines (e.g., ONNX, TensorRT
• Proficiency in low-level programming for AI accelerators, specifically developing and optimizing

🎁 Benefits

• Salary, Amazon Restricted Stock Units (RSUs), and Zoox Stock Appreciation Rights.
• Sign-on bonus may be offered as part of the compensation package.
• Comprehensive package of benefits, including paid time off (sick leave, vacation, bereavement)