Perception Deployment Engineer - Model Deployment & Optimization
At a glance
Mid-level Machine Learning Engineering role at Zoox. Foster City · full-time · $199,000–$270,000 base.
aimlroles summary, based on the employer's posting.
What you'll do
- Build real-time perception code in C++ and CUDA, keeping vehicle inference fast and memory-safe
- Reduce model size and compute through quantization, pruning and mixed-precision techniques
- Create TensorRT conversion and compilation flows for deploying models on edge hardware
- Compare compiled outputs with PyTorch for accuracy, then benchmark their latency
- Write CUDA kernels and TensorRT plugins to speed up custom operations and use accelerator memory efficiently
What you bring
- Strong production C++ and Python skills, including concurrent, memory-safe inference for real-time edge devices
- Deep experience compressing large models and applying quantization and mixed-precision inference
- Hands-on work optimizing large sensor-fusion, language or vision-language models, including attention and KV-cache methods
- Extensive experience with model conversion, compilation, latency testing and output-quality parity checks
- Low-level accelerator programming skills, including custom ML operations and CUDA kernel optimization
Who this fits
This mid-level role suits an engineer focused on deploying and optimizing perception models on vehicle systems. The work is based in Foster City and is hybrid.
From the employer
The 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.
In this role, you will:
-
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.
Qualifications:
-
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.
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 end-to-end autonomous driving paradigms (VLM/VLA models, Foundation models) and edge deployment technologies (e.g., TensorRT-LLM).
Follow us on LinkedIn
AccommodationsIf you need an accommodation to participate in the application or interview process please reach out to accommodations@zoox.com or your assigned recruiter.
A Final Note:You do not need to match every listed expectation to apply for this position. Here at Zoox, we know that diverse perspectives foster the innovation we need to be successful, and we are committed to building a team that encompasses a variety of backgrounds, experiences, and skills.