Droid Perception Intern - ML Vision for Autonomous Drones

Zipline; South San Francisco (CA); On-site; USD 57,000 - 81,000; Full time

Benefits offered by this job

Relocation support

Housing stipend

Overtime pay

Paid sick time

Other benefits

Job summary

Zipline is seeking a Droid Perception Intern in South San Francisco to explore onboard and offboard perception systems. You’ll experiment with learning-based methods, evaluate models, and contribute to real-world autonomous delivery challenges.

The role emphasizes rapid iteration, collaboration across teams, and translating research into production-ready code for deployment on drones and cloud systems.

Qualifications

• Completed at least the second year of undergraduate studies; masters/phd eligible.
• Strong foundation in 3D computer vision and camera models.
• Proven experience with deep learning frameworks and production-grade code.

Responsibilities

• Ideate, experiment and iterate on learning-based solutions for unique perception challenges.
• Collaborate closely with team members, brainstorming and deriving creative solutions from first principles.
• Leverage large datasets from heterogeneous sources (real-world, simulation, and internet-scale data) to train machine learning models.
• Ship production code to train, validate and integrate models into the perception system.
• Share findings and insights, fostering knowledge exchange across teams.

Skills

3D computer vision

Camera models

Depth estimation

Semantic segmentation

Gaussian splatting

Generative modeling

BEV-style models

VLAs

VLMs

Model optimization

PyTorch

JAX

TensorFlow

Production code

Experimentation

Education

Second year undergraduate studies

Tools

PyTorch

JAX

TensorFlow

Job description

Zipline is seeking a Droid Perception Intern in South San Francisco to explore onboard and offboard perception systems. You’ll experiment with learning-based methods, evaluate models, and contribute to real-world autonomous delivery challenges.

The role emphasizes rapid iteration, collaboration across teams, and translating research into production-ready code for deployment on drones and cloud systems.