Senior AI Inference Engineer - Model Optimization & Deployment

About the role

The Perception team is pioneering the development of a multi-modality foundation model to drive the next generation of autonomous system intelligence. As a Model Optimization & Deployment Engineer, you will focus on bringing highly efficient, production-ready large-scale models to our on-vehicle stack. We are looking for experts with hands-on experience in compressing, accelerating, and deploying complex models (LLMs, VLMs, or FMs) for power- and thermal-constrained vehicle SOCs. You will optimize ML models, write custom CUDA kernels, and build highly concurrent inference code to ensure real-time, deterministic execution on edge devices.

Responsibilities

• Optimize large-scale models (Multi-Modal Sensor Fusion models, LLMs, VLMs) using advanced quantization (PTQ, QAT), pruning, mixed-precision inference frameworks, and parameter-efficient fine-tuning (LoRA, QLoRA).
• Architect and implement model conversion and compilation pipelines using TensorRT for edge deployment.
• Perform rigorous parity checking, accuracy recovery, and latency benchmarking between PyTorch frameworks and compiled edge binaries.
• Develop and optimize custom ML OPs and TensorRT Plugins with efficient CUDA kernels to minimize latency and maximize memory bandwidth on AI accelerators.
• Write production-level, low latency, and memory-safe C++ and CUDA code for real-time inference on vehicle systems.

Requirements

• Deep expertise in model quantization (PTQ, QAT) and mixed-precision inference frameworks (INT8, FP8, FP4, BF16/FP16).
• Proven experience optimizing large-scale models (Multi-Modal Sensor Fusion models, LLMs, VLMs/VLAs) utilizing Efficient Attention mechanisms (e.g., FlashAttention, Linear Attention), KV-cache optimization (e.g., PagedAttention), and Speculative Decoding.
• Extensive experience with model conversion/compilation pipelines (e.g., ONNX, TensorRT, torch.compile) and performing rigorous latency benchmark and model quality parity evaluation.
• Proficiency in low-level programming for AI accelerators, specifically developing and optimizing custom ML OPs and TensorRT Plugins with efficient CUDA kernel implementations.
• Production-level C++ (14/17/20) and Python programming skills, with experience developing concurrent, memory-safe, real-time inference code for edge devices.

Bonus Qualifications

• Familiarity with SOTA autonomous driving perception algorithms (temporal 3D object detection, BEV, 3D Occupancy Networks) and multi-modal sensor processing (Vision, LiDAR, Radar).
• Experience with distributed training pipelines and model/tensor parallelism (PyTorch Distributed, Ray, DeepSpeed, Megatron-LM) and runtime efficiency optimization for GPU clusters.
• Experience with end-to-end autonomous driving paradigms (VLM/VLA models, Foundation models) and edge deployment technologies (e.g., TensorRT-LLM).

Pay

Base salary range: $242,000 - $290,000 per year. Compensation includes salary, Amazon Restricted Stock Units (RSUs), and Zoox Stock Appreciation Rights. A sign-on bonus may also be offered. The range applies only to base salary and varies based on geographic location and level, determined by factors such as relevant experience, domain knowledge, and interview performance.

Benefits

• Paid time off (sick leave, vacation, bereavement).
• Unpaid time off.
• Zoox Stock Appreciation Rights.
• Amazon RSUs.
• Health insurance.
• Long-term care insurance.
• Long-term and short-term disability insurance.
• Life insurance.

About Zoox

Zoox is developing the first ground-up, fully autonomous vehicle fleet and the supporting ecosystem required to bring this technology to market. Sitting at the intersection of robotics, machine learning, and design, Zoox aims to provide the next generation of mobility-as-a-service in urban environments.