Description

You will build a surgical video processing system with a dedicated kiosk interface for recording and display.

This role is on-site.

Responsibilities

• Integrate mono/stereo cameras with NVIDIA Jetson boards via MIPI CSI-2 or USB3.0.
• Build GStreamer-based pipelines for real-time, low-latency streaming and rendering.
• Develop a plug-and-play kiosk system using Qt for live streaming, file management, and playback.
• Implement AI-based depth perception using TensorRT to optimize inference on Jetson hardware.
• Configure a custom Linux-based OS for fast boot-up and automatic application launch.

Required Skills

• 6+ years of experience in embedded systems, video processing, or AI-based imaging.
• Proficiency in C/C++ and Python for embedded development.
• Hands-on experience with NVIDIA Jetson (Orin, Xavier, Nano, TX2).
• Strong expertise in GStreamer, V4L2, OpenGL, and Qt.
• Experience with Linux kernel, drivers, and fast boot optimizations.
• Knowledge of AI-based depth estimation models like MiDaS, FastDepth, or MonoDepth2.
• Experience with TensorRT, OpenCV, and Deep Learning frameworks (PyTorch, TensorFlow).
• Familiarity with camera interfaces (MIPI CSI-2, USB) and sensors (Sony IMX, Basler).
• Understanding of secure file handling and medical regulatory standards.

Preferred Skills

• Previous experience with medical imaging or real-time video processing.
• Experience working with stereo vision and 3D depth mapping.

Key Skills

Education

Any Graduate