Lead - Computer Vision

Lead Computer Vision

Computer Vision, Deep Learning, Edge AI, Linux, and GStreamer

The incumbent will lead the design and deployment of real-time vision algorithms on embedded platforms and mobile devices, transforming innovation into scalable commercial products.

Key Responsibilities

• Lead end-to-end development of computer vision and deep learning solutions for edge devices such as smart cameras, biometric terminals, and IoT vision systems.
• Architect and optimize real-time video pipelines using GStreamer on Linux-based embedded platforms.
• Design and implement DL/CV models (object detection, segmentation, tracking, gesture recognition, facial analytics, etc.) using TensorFlow, PyTorch, OpenCV, DLIB, Mediapipe, and TFLite.
• Drive AI model lifecycle management dataset curation, training, validation, quantization, and deployment on embedded/edge hardware.
• Collaborate with cross-functional teams for hardware integration, firmware communication, and cloud/mobile interfacing.
• Ensure robust video streaming, processing, and performance optimization for real-time applications using GStreamer and multimedia APIs.
• Lead a team of engineers, promoting R&D excellence, mentoring talent, and generating IP/patents.
• Collaborate with product and design teams to transform research ideas into production-grade solutions.
• Stay ahead of emerging trends in Edge AI, CV frameworks, and embedded vision architectures.

Required Skills & Technical Expertise

Must Have:

• Strong expertise in Linux-based development and GStreamer multimedia framework (pipeline design, custom plugin development, optimization for video capture and streaming).
• Proficiency in C/C++ and Python programming for performance-critical applications.
• Hands-on experience with Computer Vision and Deep Learning frameworks TensorFlow, PyTorch, OpenCV, DLIB, Mediapipe, and TFLite.
• Experience in Edge AI inference optimization (quantization, pruning, and deployment on NPUs/DSPs/ARM platforms).
• Solid understanding of image and video processing techniques, including object detection, recognition, tracking, segmentation, and gesture recognition.
• Exposure to Android/iOS camera systems, embedded Linux, and real-time video analytics.
• Experience in software architecture design for camera-based AI products (Edge + Cloud integration).
• Excellent problem-solving, debugging, and system-level understanding of video processing pipelines.

Good to Have:

• Exposure to biometric systems (face, iris, fingerprint).
• Experience with multimedia middleware (V4L2, FFmpeg).
• Familiarity with 3D vision, SLAM, or sensor fusion.
• Understanding of IoT and secure data streaming architectures.

Qualification & Experience

• B.Tech/M.Tech/Ph.D. in Computer Science, Electronics, or related field
• Experience in Computer Vision, Deep Learning, Linux, and GStreamer-based systems
• Proven track record of developing and deploying AI-driven camera products or embedded vision systems