Senior AI Inference Engineer - Model Optimization & Deployment

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 the ML models, write custom CUDA kernels, and build highly concurrent inference code to ensure real‑time, deterministic execution on edge devices.

• 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 Tensor
  
  RT 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 Tensor
  
  RT 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.

• 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., Flash Attention, Linear Attention), KV‑cache optimization (e.g., Paged Attention) and Speculative Decoding.
• Extensive experience with model conversion/compilation pipelines (e.g., ONNX, Tensor
  
  RT, torch.compile) and performing rigorous latency benchmark and model quality parity valuation.
• Proficiency in low‑level programming for AI accelerators, specifically developing and optimizing custom ML OPs and Tensor
  
  RT 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.

• 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, Deep Speed, 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., Tensor
  
  RT-LLM).

$242,000 - $290,000 a year

There are three major components to compensation for this position: salary, Amazon Restricted Stock Units (RSUs), and Zoox Stock Appreciation Rights. A sign‑on bonus may be offered as part of the compensation package. The listed range applies only to the base salary. Compensation will vary based on geographic location and level. Leveling, as well as positioning within a level, is determined by a range of factors, including, but not limited to, a candidate's relevant years of experience, domain knowledge, and interview performance.

The salary range listed in this posting is representative of the range of levels Zoox is considering for this position.

If you need an accommodation to participate in the application or interview process please reach out to [email protected] or your assigned recruiter.