Software Engineer, Sensor Fusion and Machine Learning

About the position

Meta is building the Metaverse, the "spatial internet" where immersive virtual worlds will coexist with the real world. The Spatial AI team under Reality Labs (RL) develops cutting-edge technologies that serve as the foundation of Meta AR/VR products. From tracking & localization to context/semantic understanding, our team takes new technologies from early concept to the product level while prototyping and realizing the new experiences they open up. We are looking for software engineers who are passionate about building tracking & positioning solutions for AR/VR devices. In this role, you will be involved in novel technology development using a variety of sensors for inertial and visual motion tracking, spatial mapping & understanding, and sensor fusion for positioning and places identification. You will collaborate with other engineers and researchers in deploying such solutions in RL devices and light-up the next generation experiences such as world-locked rendering, AI powered spatial recommendation, and fitness tracking.

Responsibilities

• Develop tracking and positioning solutions for AR/VR devices.
• Utilize a variety of sensors for inertial and visual motion tracking.
• Implement spatial mapping and understanding techniques.
• Conduct sensor fusion for positioning and place identification.
• Collaborate with engineers and researchers to deploy solutions in RL devices.
• Contribute to the development of next-generation experiences such as world-locked rendering and AI-powered spatial recommendations.

Requirements

• Bachelor's degree in Computer Science, Computer Engineering, or a relevant technical field, or equivalent practical experience.
• Industry experience coding with C++ and Python for design and development of tracking, sensor fusion, and machine learning technologies and systems.
• Experience in designing software systems and machine learning models targeted for edge devices.
• Demonstrated familiarity with modern machine learning algorithms and experience with frameworks such as PyTorch.
• PhD degree in Computer Science, Computer Vision, Machine Learning, Robotics, or a related technical field.
• Experience in inertial/visual motion tracking, Kalman filters, and state estimation.
• Experience with neural inertial fusion and visual or wireless positioning.
• Experience in mobile optimization and DSP acceleration.
• Familiarity with the Android Open Source Project.
• Experience handling sensors such as IMU, magnetometer, WiFi/BLE, Camera, and GNSS.
• Knowledge of common digital signal processing techniques such as digital filtering, Fourier transform, correlation, and modulation.