Senior/Staff Software Engineer - Machine Learning & System Optimization
At a glance
Senior Machine Learning Engineering role at Zoox. Foster City · full-time · $254,000–$350,000 base.
aimlroles summary, based on the employer's posting.
What you'll do
- Balance CPU, GPU, and interconnect capacity among perception models and inference engines running on the vehicle
- Improve compute use by combining perception models and changing how inference work is scheduled
- Reduce model cost with quantization, pruning, mixed-precision inference, and parameter-efficient tuning
- Build TensorRT conversion and compilation pipelines, then write low-latency C++ and CUDA for real-time inference
What you bring
- Deep experience tuning CPU and GPU systems for low latency or high throughput
- Strong command of real-time limits, including processing delay, memory use, and bandwidth pressure
- Expertise in quantization and mixed-precision inference, including formats such as INT8, FP8, FP4, and BF16/FP16
- Production C++ and Python skills, with experience building concurrent, memory-safe inference for edge devices
Who this fits
This senior role suits an engineer who has optimized and deployed complex models on constrained vehicle hardware. It is based in Foster City and listed as hybrid. Robotics, autonomous-driving perception, multimodal sensor processing, or TensorRT-LLM experience is an added advantage.
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 Machine Learning and System Optimization Engineer, you will orchestrate and allocate overall system capacity to various core perception models running on-bot, as well as drive large initiatives that allow for more efficient inference by sharing various parts of the perception stack with one another.
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 compressing, accelerating, and deploying complex models, including LLMs, VLMs, or foundation models, for power- and thermal-constrained vehicle SoCs.
In addition, you will optimize 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:
-
Allocate and distribute system resources (CPU/GPU/interconnect) to various models and inference engines running on the robot.
-
Spearhead cross-cutting initiatives that allow for better compute utilization through sharing/fusing models and better scheduling strategies.
-
Optimize large-scale models (Multi-Modal Sensor Fusion models, LLMs, VLMs) using advanced quantization (PTQ, QAT), pruning, mixed-precision inference frameworks, and parameter-efficient fine-tuning (LoRA, QLoRA).
-
Architect and implement model conversion and compilation pipelines using TensorRT for edge deployment.
-
Write production-level, low-latency, and memory-safe C++ and CUDA code for real-time inference on vehicle systems.
Qualifications:
-
Deep experience in system and performance optimization in CPU/GPU systems designed for low latency or high throughput.
-
Deep expertise in working with real-time systems & required constraints such as processing latency, memory utilization, and memory bandwidth pressure.
-
Deep expertise in model quantization (PTQ, QAT) and mixed-precision inference frameworks (INT8, FP8, FP4, BF16/FP16).
-
Proficiency in low-level programming for AI accelerators, specifically developing and optimizing custom ML OPs and TensorRT Plugins with efficient CUDA kernel implementations.
-
Production-level C++ (14/17/20) and Python programming skills, with experience developing concurrent, memory-safe, real-time inference code for edge devices.
Bonus Qualifications:
-
Prior experience in high-performance robotics applications such as AV/drones/robots.
-
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.