Role: Computer Vision / Machine Learning Engineering
Location: United States · Redwood, CA
About the opportunity
Our client is pioneering intelligent robotics solutions that positively transform how the world works, freeing people from repetitive and physically demanding tasks so they can focus on creative, problem-solving work that humans do best. Starting with warehouse automation, their full-stack robotics systems pick, move, pack, and collaborate with human-like skill, awareness, and learning capabilities. Their systems are software driven, hardware-agnostic, and already operating at scale in production environments across global supply chains.
As a Senior Computer Vision Engineer, you'll work at the intersection of Computer Vision and Machine Learning understanding current system limitations, bringing deep domain expertise, and developing next-generation models and pipelines. You'll own the end-to-end process: from data gathering, augmentation, labelling, and dataset curation, through model training, deployment, and field troubleshooting. The role demands low-latency, near-real-time inference, requiring highly performant models and serving architectures built from the ground up not just adapted from open-source solutions.
What You'll Do
- Write production-grade Computer Vision code and build ML models tailored for real-world robotic environments
- Understand existing systems and their limitations, and apply expertise to improve accuracy and robustness
- Update and scale current ML pipelines to cover broader scenarios and edge cases
- Apply expertise in semantic segmentation and instance segmentation, staying current with the latest research and implementing state of the art approaches using PyTorch, TensorFlow, or equivalent frameworks
- Work extensively with RGBD datasets and point clouds to solve perception challenges in robotics and automation
- Build highly performant, low-latency inference pipelines that approach real-time performance
- Design and maintain training and serving pipelines on cloud infrastructure
- Curate datasets, study model performance, and drive continuous quality improvement
- Deploy, monitor, and troubleshoot models in live production and field environments
What Are We Looking For?
Required:
- BS/MS in Computer Science, Machine Learning, or a related discipline, or equivalent experience
- 5+ years of relevant work experience in Computer Vision and ML engineering
- Strong proficiency with OpenCV and Open3D
- Proven experience building, training, and deploying production ML models from scratch using PyTorch and TensorFlow
- Strong command of Modern C++ and Python
- Experience using profilers and debuggers to optimise code for performance
- Experience with model serving architectures such as NVIDIA Triton, TorchServe, TensorFlow Serving, or Flask
- Solid academic grounding in ML theory with the ability to read, interpret, and implement research papers
- Experience with cloud infrastructure (AWS, GCP, or Azure) for building training and serving pipelines
- Ability to trace and resolve problems across interconnected systems, pipelines, and applications
- Experience with Git and modern CI pipelines
Nice to Have:
- Experience with Docker and Kubernetes
- Previous startup experience
Why You'll Love Working Here
- Join one of the fastest-growing companies in robotics, backed by world-class investors in the deep tech space
- Work on cutting-edge perception systems that are already deployed and picking millions of goods in production
- Be part of a diverse, multidisciplinary team built on passion, trust, and a customer-obsessed culture
- Help shape the future of intelligent automation at a company where every decision is driven by real-world impact
