AI Inference Engineer - Model Optimization & Deployment

Zoox•San Diego, CA

14h

About The Position

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.

Requirements

Deep expertise in model quantization (PTQ, QAT) and mixed-precision inference workflows (INT8, FP8, INT4, BF16/FP16).
Proven experience optimizing large-scale models (LLMs, VLMs, or VLAs) utilizing KV-cache optimization (e.g., PagedAttention), Speculative Decoding, and Efficient Attention mechanisms (FlashAttention, Linear Attention).
Extensive experience with model conversion/compilation pipelines (TensorRT, TensorRT-LLM) and performing rigorous parity/latency benchmarking.
Proficiency in low-level programming for AI accelerators, specifically writing and optimizing custom CUDA kernels and TensorRT Plugins.
Production-level C++ (14/17/20) and Python programming skills, with experience writing concurrent, memory-safe, real-time inference code for edge devices.

Nice To Haves

Experience with distributed training pipelines and model/tensor parallelism (PyTorch Distributed, Ray, DeepSpeed, Megatron-LM) and runtime efficiency optimization for GPU clusters.
Familiarity with autonomous driving perception stacks (temporal 3D object detection, BEV, 3D Occupancy Networks) and processing multi-modal sensor streams (Vision, LiDAR, Radar).
Understanding of end-to-end autonomous driving paradigms (VLA models, closed-loop simulation validation).

Responsibilities

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