Zipline is looking to improve the reliability and performance of its drone delivery system by enhancing its state estimation capabilities, particularly in challenging environments with intermittent GNSS availability and potential sensor failures.
Requirements
- Experience with state estimation, probabilistic filtering, GNSS RTK and raw measurements, IMU data, sensor modeling and simulation.
- Understanding of calculus, linear algebra, non-linear optimization, and computational numerical methods.
- Experience in building high performance software systems using compiled languages (C/C++/Rust/Ada/etc.).
Responsibilities
- Extract the maximum value from the observations of our GNSS hardware: integrating all the data available from our ground station network when available, but also building robust systems which handle extended communications outages without a large amount of drift.
- Design systems which deal with intermittent GNSS availability, ensuring our vehicle can make use of both GNSS and vision data, while handling failures in either one at any time.
- Perform trade studies to understand the value of new sensors or processing approaches to vehicle performance and reliability.
- Analyze the performance of systems both in simulation and using data from vehicles operating in the field to find under-performing facets of the system, and devise solutions which bring them up to speed.
- Participate in code review with a strong and capable team of engineers building highly reliable software in the Rust programming language.
Other
- A degree in physics or an engineering discipline.
- The capability to solve complex problems with little supervision as part of an integrated team.
- Excellent communication skills, both written and verbal.
