Flyzipline

Flyzipline

Autonomy Droid Perception SWE - Onboard Systems

South San Francisco, California, USA

Sponsorship not specified$200k-$240kDetected 20 hours ago
Machine LearningDeep LearningData EngineeringNLPComputer VisionA/B TestingRoadmappingLogisticsRoboticsSensorsResearchAdaptability

About the role

  • About Zipline Zipline is the world's largest and most experienced drone delivery service.
  • Today, Zipline operates on four continents, makes a delivery somewhere in the world every 30 seconds, and has completed millions of deliveries to date, including blood, vaccines, medical supplies, food, and retail products.
  • The drone is only 15% of what we've built to enable seamless, reliable, global operations.

Responsibilities

  • Implement, train and evaluate real-time 3D perception models that work with two or more cameras across one or more timesteps
  • Deploy and run these models onboard a resource-constrained computer, finding ways to optimize and reduce compute and memory footprints
  • Build visualization, introspection and eval tooling to deeply understand model performance both on test datasets as well as "in the wild"
  • Work closely with the motion planning team, building an expressive yet compact interface between the two subsystems and tracking the right metrics to ensure we're always hill-climbing towards a better overall system
  • At the Senior level, you'll lead architectural decisions, drive experimentation, and own outcomes for a particular model head or backbone.
  • At the Staff level, you will own roadmapping the future of one or more onboard models and manage cross-functional interfaces in addition to the above.
  • Stay up to date with research in the field, drive experimentation, go to conferences and help keep Zipline's ML modeling stack in lockstep with powerful new paradigms in real-time compute-constrained 3D perception

Requirements

  • As we expand into increasingly complex, safety-critical environments, the ML systems behind our autonomy stack must be robust, adaptable, and deeply integrated with the hardware.

Nice to have

  • ML experience on hardware applications is a strong plus - a robot will move based on the outputs of your perception system

Compensation

  • The total compensation package for this role may also include: equity compensation; overtime pay; discretionary annual or performance bonuses; sales incentives; benefits such as medical, dental and vision insurance; paid time off; and more.

Benefits

  • Strong understanding of classical computer vision (e.g. camera calibration, epipolar geometry, structure-from-motion, SGBM stereo) and the ability to blend it with modern ML approaches.

This listing is sourced directly from Flyzipline's careers page and normalized into a canonical job model.