RealSense delivers industry-leading depth cameras and vision technology used in autonomous mobile robots, humanoids, access control, industrial automation, healthcare and more. With a mission to deliver world class perception systems for Physical AI and safely integrate robotics and AI into everyday life, RealSense provides intelligent, secure and reliable vision systems that help machines navigate and interact with the human world.

We are looking for a  skilled and independent software engineer  to join our team and take a key role in developing and maintaining our facial biometrics solution. This solution involves a complex pipeline that integrates deep learning algorithms and real-time communication between embedded devices and host systems.

As part of a fast-paced startup environment, you'll be expected to take ownership, think system-wide, and contribute hands-on to a high-impact product used in real-world applications.

Key Responsibilities

• Implement, and maintain software for facial biometrics and computer vision applications
• Develop in C++ and C on Linux-based embedded platforms
• Work closely with algorithm and hardware teams to integrate deep learning models into a robust pipeline
• Debug and optimize complex systems involving real-time data processing and device-host communication
• Ensure system stability, performance, and scalability
• Take end-to-end ownership of features from design to deployment
• Contribute to architectural decisions and code reviews in a collaborative environment

Requirements

• 4+ years of hands-on experience in  C++ and C  development
• Strong software engineering and  debugging skills
• Experience with  embedded systems  and performance/resource constraints
• Proven ability to work independently and  own complex components
• Understanding of  system-wide architecture  and integration of various modules

Nice to Have

• Background in  computer vision  or  deep learning inference
• Familiarity with frameworks like OpenCV, TensorFlow, or ONNX Runtime
• Experience with device–host communication protocols (e.g., USB, UART, TCP/IP)
• Exposure to startup environments or fast-moving product development cycles