Develop systems and algorithms to find and track objects of interest found in camera imagery and other sensor data. Teach robots to know what they are looking at, or where they should be looking. The awesome, fun stuff that you will do:
• Develop multi-modal detection, classification & tracking algorithms
• Guide relevant system architecture
• Research and characterize new approaches and algorithms
• Take algorithms from initial development through product delivery
• Optimize for computationally constrained environments
• Work with a collaborative, fast-paced team excited about product mission
• Dodge robots flying overhead
The following attributes are useful:
• Strong understanding of state-of-the-art CNN object detectors
• Strong understanding of state-of-the-art object tracking systems
• Experienced configuring and tuning neural networks.
• Proficiency with GPU programming
• Proficiency with Caffe/Torch/Tensorflow/OpenCV
To conform to U.S. Government regulations, applicant must be a U.S. citizen, lawful permanent resident of the U.S., protected individual as defined by 8 U.S.C. 1324b(a)(3), or eligible to obtain the required authorizations from the U.S. Department of State.
We empower robots to go where people and robots cannot go today - to gather critical intelligence that makes battlefields safer for service members and innocent civilians. We do cool stuff related to perception, SLAM, exploration planning, path planning, controls, multi-agent operations, and hardware design.