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 (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.
- 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.
- 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).
About Zoox
Zoox is developing the first ground-up, fully autonomous vehicle fleet and the supporting ecosystem required to bring this technology to market. Sitting at the intersection of robotics, machine learning, and design, Zoox aims to provide the next generation of mobility-as-a-service in urban environments. We’re looking for top talent that shares our passion and wants to be part of a fast-moving and highly execution-oriented team.
Accommodations
If 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.
Average salary estimate
If an employer mentions a salary or salary range on their job, we display it as an "Employer Estimate". If a job has no salary data, Rise displays an estimate if available.
Zoox is hiring a skilled C++ software engineer to design and maintain high-performance, safety-critical drivers for lidar, radar, and camera sensors that feed the autonomous driving stack.
Lithic seeks a Senior Software Engineer, Data Platform to build production Python backend services and REST APIs that reliably expose Snowflake-powered data to internal consumers.
Experienced C++ engineers are needed to evaluate, repair, and improve AI-generated code as contractor contributors to an RLHF pipeline.
Work with Vendelux's Product Engineering team to build user-facing full-stack features and gain hands-on startup engineering experience in a backend-focused, remote-friendly internship.
Work directly with the founder to harden rapid AI-driven prototypes into battle-tested, frontend-forward foundations for an early-stage precision medicine platform.
Point72 is hiring a Machine Learning Infrastructure Engineer to build and operate scalable GenAI infrastructure that accelerates model development and production across cloud and on-prem environments.
Alegeus is hiring a Software Engineer II to design, develop, and maintain .NET-based SaaS applications that support fintech and healthtech solutions in a collaborative, hybrid environment.
Work remotely as a Front-End Application Developer building accessible, scalable React/Angular applications for environmental data platforms while contributing across the full stack.
Evaluate and optimize real-world AI workloads on emerging hardware platforms to bridge the gap between expected and observed system performance for OpenAI’s infrastructure.
NVIDIA's NVHPC compilers & tools group seeks a Senior HPC Performance Engineer to analyze and optimize high-performance applications across CPU and GPU architectures and guide compiler and application engineering improvements.
Lead and mentor a software engineering team at Renesas to deliver high-quality embedded and application software while driving execution and cross-functional collaboration.
Experienced backend-focused full-stack engineer to build and maintain scalable Ruby on Rails services integrated with React and GraphQL for a healthcare data intelligence platform.
A growing IT services firm is hiring a Jr. Full Stack .NET Developer to implement .NET Core web applications, APIs, and database solutions in a collaborative team environment.
Senior Architect role to design and implement high-performance AI communication and memory libraries while driving hardware-software co-optimization across GPUs, DPUs, NICs, and interconnects at NVIDIA.
Zoox was founded to make personal transportation safer, cleaner, and more enjoyable—for everyone. To achieve that goal, the team created a whole new form of transportation. Zoox will provide mobility-as-a-service in dense urban environments.
31 jobs
🔮
Hi, I'm Risa! Your AI Career Copilot
you, just ask me below!
