3D Vision Engineer - Dynamic Perception Data (TDG)
Santa Clara Valley (Cupertino), California, United States
Machine Learning and AI
Do you want to push the limits of the best Augmented Reality platform in the world? Apple's Technology Development Group (TDG) delivers algorithms that drive revolutionary Apple products, including the augmented reality (AR) platform ARKit to create ground-breaking new products. In this position, you will have the opportunity to be part of our extraordinary team of computer vision and deep learning researchers and engineers to discover and build solutions to previously-unsolved challenges and push the state of the art in AR algorithms that will change the way people experience the world! We are looking for a driven computer vision software engineer, optimally with experience in motion capture, sensor fusion, and interactive 3D UI tool creation to invent and develop hardware and software solutions for dynamic 3D data collection and annotation. As a member of a fast-paced team, you have the rewarding opportunity to shape upcoming products that will delight and inspire millions of people every day. To succeed within this role, you should have shown experience in several of the following areas:
- Strong C++ experience, including modern C++
- Strong experience in Python. Including popular science libraries like Numpy, Pandas, … etc.
- Solid understanding of 3D computer vision and multi-camera systems.
- Experience in sensor fusion and calibration.
- Experience in interactive 3D graphics programming/UI tool development.
- Excellent communication and collaboration skills
- Excellent problem solving and analytical thinking skills
- Track record of successfully building and shipping products or open source projects
- Creativity and curiosity for solving highly complex problems
- Bonus for iOS development experience
- Bonus for experience in Swift or Objective-C
You’ll be working in a team of computer vision and deep learning researchers and engineers to implement world class algorithms that pushes the state of the art. Your goal is to design and drive building a novel infrastructure for collecting and annotating 3D data in dynamic environments that enables the team to measure their progress accurately across all target scenarios. Your job responsibilities will include: -Working with cameras, IMUs, motion capture systems and robots to define and build multi-sensor data capture setups. -Developing 3D computer vision and sensor fusion algorithms. -Building UI tools for visualizing and interacting with multi-modal 3D data. -Improving and extending existing tools and frameworks. -Collaborating with CVML engineers and researchers in order to define quality metrics and regression tests. -Cooperating with your team members to prepare presentations, papers, and talks to explain your inventions.
Education & Experience
M.S., or Ph.D. or 5+ years of industry experience in computer vision, machine learning or robotics or related fields