We sent a six-digit code to . Enter it below — or use the link in the same email.
Or click the link in the same email — either works.
Enter the email address on your account and we'll send you a link to set a new password.
Remembered it? Sign In
Zoox
NewThe Perception team is pioneering the development of a multi-modality foundation model to drive the next generation of autonomous system intelligence.
As a Perception 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 computer vision or foundation models 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.
Design and develop production-level, low latency, and memory-safe C++ and CUDA code for real-time perception algorithms on vehicle systems.
Optimize large-scale models (Multi-Modal Sensor Fusion models, LLMs, VLMs) using advanced quantization (PTQ, QAT), pruning, mixed-precision inference frameworks.
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.
Production-level C++ (14/17/20) and Python programming skills, with experience developing concurrent, memory-safe, real-time inference code for edge devices.
Deep expertise in model compression technologies (e.g., model quantization such as PTQ and QAT) and mixed-precision inference frameworks (INT8, FP8, 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.
Extensive experience with model conversion/compilation pipelines (e.g., ONNX, TensorRT, 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 TensorRT Plugins with efficient CUDA kernel implementations.
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 end-to-end autonomous driving paradigms (VLM/VLA models, Foundation models) and edge deployment technologies (e.g., TensorRT-LLM).
Here is what this employer asked for. Sign in and we will fill in your half.
Zoox, an Amazon subsidiary, develops an autonomous ride-hailing service and a purpose-built electric robotaxi. Rather than adapting a conventional car, it designed a bidirectional vehicle around autonomous operation, passenger use, and dense urban mobility. The company develops the vehicle, autonomous-driving software, sensing, simulation, fleet systems, and rider experience as one integrated service. Zoox is progressing from testing toward commercial robotaxi operations with safety and controlled deployment at the center of its approach.
Search by role, company, or anything a posting mentions.
