Computer Vision Researcher/Engineer for ground-breaking Augmented Device start-up in Sunnyvale, CA
We have an exciting opportunity on our Software team for a strong member with exceptional development/research skills in the field of Computer Vision and Machine Learning.
The primary responsibility is to drive the research and development of core perception components within the agreed upon scope and schedule as defined by the management team.
Must have expertise in at least one of the following core technical areas of geometric vision and machine learning: sensor calibration (cameras, IMUs, displays), visual inertial odometry, dense environment mapping, eye tracking, 3D scene understanding.
- Involved in research and development effort of advanced product-critical computer vision components covering key product critical perception features such as head pose tracking, eye tracking, environment mapping, sensor calibration.
- Work hand-in-hand with the key stakeholders and developers across the company using computer vision components.
- Support overall research engineering and architecture efforts of computer vision and machine learning components.
- Write maintainable, reusable code, leveraging test-driven principles to develop high-quality geometric vision and machine learning modules.
- Troubleshoot and resolve software defects and other technical issues.
- Act as a mentor and subject matter expert within the computer vision group and with other key stakeholders.
- Review individual developer's code in the team to ensure the highest code quality in Computer Vision components.
Must have Skillsets:
- 2-5+ years of working experience in Computer Vision targeted to product development.
- Fluent in C/C++ (programming and debugging)
- Experience working with OpenCV.
Must have experience in at least one of the following areas:
- Sensor Calibration: Design and implement algorithms for online and offline calibration of complex devices composed of several sensors, cameras, IMUs, depth sensors, and imagers. Collaborate with other engineers on the design and deployment of a fully automatic robotics-aided calibration process targeted for factory production.
- Visual-Inertial Pose Tracking: Design and implement advanced algorithms for estimating the 3D pose of a head-mounted device by optimally fusing visual and inertial measurements collected from multiple cameras and IMUs.
- Dense Mapping: Design and implement advanced algorithms for reconstructing dense 3D models of large-scale indoor environments using depth sensors.
- 3D Scene Understanding: Design and implement 3D scene segmentation algorithms based on depth, motion or texture data.
- Eye Tracking: Design and implement advanced algorithms for real-time stereoscopic eye vergence tracking in 3D.
- Hand Gesture Tracking: Design and implement advanced algorithms for real-time detection and tracking of hand gestures in 3D.
- 3D Object Tracking: Design and implement robust algorithms for detecting and tracking the 6 DOF pose of known moving objects from multiple cameras in presence of clutter and occlusions.
- Experience in Deep Learning is strongly preferred with knowledge of at least one of TensorFlow, PyTorch, or Caffe.
- Knowledge of parallel computing, OpenCL, CUDA, GPGPU is a plus.
- Knowledge software optimization and embedded programming is a plus
- MS in Computer Science or Electrical Engineering
- Ph.D. is preferred
Location: Sunnyvale, CA
Duration: Fulltime opportunity, relocation assistance, excellent benefits.