Perception Deployment Engineer - Model Deployment & Optimization
Hybrid (Foster City, CA / Boston, MA / Seattle, WA / San Diego, CA)$199k - $270kFull-timePosted 2w ago
About the role
Role focused on bringing production-ready, large-scale models to on-vehicle stacks through compression, acceleration, and edge deployment optimization using CUDA kernels and real-time inference for power- and thermal-constrained SOCs.
Responsibilities
- 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 quantization (PTQ, QAT), pruning, and mixed-precision inference frameworks.
- Architect and implement model conversion and compilation pipelines using TensorRT for edge deployment.
- Perform parity checking, accuracy recovery, and latency benchmarking between PyTorch 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 in concurrent, memory-safe, real-time inference code for edge devices.
- Deep expertise in model compression technologies (PTQ, QAT) and mixed-precision inference frameworks (INT8, FP8, BF16/FP16).
- Proven experience optimizing large-scale models (Multi-Modal Sensor Fusion models, LLMs, VLMs/VLAs) with Efficient Attention mechanisms (FlashAttention, Linear Attention) and KV-cache optimization (PagedAttention).
- Extensive experience with model conversion/compilation pipelines (ONNX, TensorRT, torch.compile) and latency benchmarking and model quality parity valuation.
- Proficiency in low-level programming for AI accelerators, including developing and optimizing custom ML OPs and TensorRT Plugins with CUDA kernels.
Skills
Required:C++PythonModel compressionCUDATensorRTLow-level AI accelerator programming
Nice to have:ONNX
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
Last updated Oct 21, 2026. Interested? Apply on the company site.
About Zoox
It's Not a Car | Zoox
Zoox is a purpose-built autonomous vehicle designed for riders, not drivers. Learn more about the Zoox robotaxi and the future of ride-hailing.
autonomous vehiclerobotaxiride-hailing
More open roles at Zoox
- Contract Student Worker - Freeways Data Evaluation (20 hrs/wk)5d agoHybrid (Foster City, CA) · Zoox Internships – Software
- Software Engineer, ML Training Optimization5d agoFoster City, CA · Software Systems
- Strategic Sourcing Manager, IT Software & Services5d agoHybrid (Foster City, CA) · Supply Chain Quality and Reliability – Indirect Procurement
- Program Analyst5d agoFoster City, CA · Vehicle Development – Vehicle Program Management
- Hardware Engineer - Test Development5d agoFoster City, CA · Vehicle Development – Vehicle Integration, Testing & Validation