Responsibilities
- Design and implement computer vision machine learning models running in the cloud or on Zipline’s on-premises GPU cluster.
- Train and deploy large-scale models for semantic segmentation, feedforward 4D geometry, and learned preference modeling.
- Use aerial survey images, production delivery data, and synthetically generated data to develop perception systems.
- Build tools that predict deliverability, generate high-fidelity priors, and reduce customer onboarding friction in new environments.
- Design evaluation and validation infrastructure to ensure models operate reliably in the field.
- Ship production features or models on an approximately six-week cycle.
- At the Senior level, lead architectural decisions and drive experimentation; at the Staff level, own roadmaps for one or more offboard models.
Requirements
- At least 5 years of experience building and deploying deep learning-based perception systems for Senior candidates, or 8 years for Staff candidates.
- Experience with 3D geometry, semantic understanding, or mapping from remote sensing data.
- Strong knowledge of classical computer vision, including camera calibration, epipolar geometry, and structure-from-motion.
- Experience combining classical computer vision with feedforward multi-view models and gaussian splats.
- Hands-on experience training, fine-tuning, iterating on, and optimizing CNN, transformer, and foundation-style model architectures in production.
- Familiarity with training, data annotation, and evaluation pipelines.
- Ability to work across data pipelines, training infrastructure, and distributed training debugging.
- Experience deploying models in real-world, high-stakes robotics or autonomy applications is preferred for Senior candidates and required for Staff candidates.
- Staff candidates should have experience initiating new efforts and creating staged roadmaps for challenging machine learning tasks.
Categories
About Zipline
Zipline was founded to create the first logistics system that serves all humans equally. Our aim is to solve the world’s most urgent and complex access challenges. Leveraging expertise in robotics and autonomy, Zipline designs, manufactures and operates the world’s largest automated delivery system. Zipline serves tens of millions of people around the world and is making good on the promise of building an equitable and more resilient global supply chain. From powering Rwanda’s national blood delivery network and Ghana’s COVID-19 vaccine distribution, to providing on-demand home delivery for Walmart and enabling leading healthcare providers to bring care into the home in the United States, Zipline is transforming the way goods move. By transitioning to clean, electric, instant logistics, we can decarbonize delivery, decrease road congestion, and reduce fossil fuel consumption and air pollution, while providing equitable access for billions of people. The technology is complex but the idea is simple: a teleportation service that delivers what you need, when you need it. Zipline is inspiring people, governments, and businesses to imagine what is possible when goods can move as seamlessly as information. To join the team, check out our career page: https://flyzipline.com/careers/