About the Droid Planning Team 

The Droid Autonomy team owns the entire autonomy stack behind droid package pickup and delivery. This includes perception (understanding the world), high-level decision making (executing behaviors), and motion planning (navigating through obstacles to deliver packages safely and efficiently). It’s an extremely cross-functional team that brings together expertise in robotics, machine learning, planning, and systems engineering—working as one to make the droid a safe, reliable, and scalable real-world delivery system.

The Role 

• Work hands-on with an autonomous robot operating in the real world — to help expand its capabilities for safer and more reliable deliveries.
• Analyze, validate real-world data to understand system performance and identify failure modes and come up with unique solutions.
• Design experiments and models that improve the robot’s ability to make reliable decisions in highly variable, unpredictable environments.
• Translate insights from validation into actionable improvements that directly impacts the speed, accuracy and safety of the robot delivery.
• Collaborate closely with perception, autonomy, and flight testing teams to see how your work connects across the full robotics stack.
• Gain experience with the end-to-end process of deploying autonomy at scale—from data collection and model development through validation and live operations
• Be part of an extremely motivated team that is delivering real-world solutions at scale, not just research prototypes.

What You'll Do  

• Work with and iterate on a state-of-the-art autonomous system: analyze flight data, extract key features of the droid’s performance, and identify what it takes to improve motion planning in difficult and uncertain environments.
  Apply data analysis, statistics, and machine learning techniques to increase the reliability and robustness of the droid’s deliveries.
  Design and run validation experiments to measure success and failure rates under different real-world conditions (e.g., driveway geometry, car presence, time of day).
  Develop tools and pipelines to evaluate motion planning models, quantify uncertainty, and connect improvements directly to field performance.

What You'll Bring  

• Currently pursuing a Master’s in CS, EE, Robotics, or a related field with a familiarity with learning-based planning methods.
• Software Proficiency and the ability to write safe and performant code; willing to learn new languages and adapt.
• Statistical reasoning & validation mindset: able to design experiments, account for bias/variance, quantify confidence, and interpret results to guide decisions.
• Structured problem solver: can break ambiguous, real-world problems into hypotheses and executable plans; comfortable making and testing assumptions.
• Able to work in person at our office and thrive in a collaborative, hands-on environment.

What Else You Should Know

The final cash pay for this role will depend on a variety of factors, including a specific candidate's experience, qualifications, skills, and working location. The total compensation package for each role may also include: a housing stipend; overtime pay; relocation support; paid sick time; and more. 

Zipline is an equal opportunity employer and prohibits discrimination and harassment of any type without regard to race, color, religion, age, sex, national origin, disability status, genetics, protected veteran status, sexual orientation, gender identity or expression, or any other characteristic protected by federal, state or local laws or our own sensibilities.

We value diversity at Zipline and welcome applications from those who are traditionally underrepresented in tech. If you like the sound of this position but are not sure if you are the perfect fit, please apply!

Zipline is also committed to providing reasonable accommodations to individuals with disabilities. Please let your point of contact at Zipline know if you require any accommodations throughout your interview process.