Computer Vision Architect/ Lead
Infosys
Infosys
Join our team as a Computer Vision Architect/Lead and drive innovation in real-time image and video analytics. This role requires a deep understanding of computer vision, advanced deep learning frameworks, and efficient edge deployment strategies. You will be instrumental in developing and implementing cutting-edge solutions.
As a key member of our Engineering Services unit, you'll leverage your expertise to tackle complex challenges and contribute to high-impact projects within Infosys Limited.
Design, train, and optimize deep learning models for diverse computer vision tasks, including object detection, image recognition, segmentation, and video analytics. Lead extensive real-time implementations managing over 100 video streams. Fine-tune models like CNNs and Vision Transformers using frameworks such as TensorFlow, PyTorch, and ONNX. Build and deploy robust inference pipelines leveraging NVIDIA technologies like NGC models, TAO Toolkit, DeepStream Metropolis, and Triton Server. Apply sophisticated pre- and post-processing techniques to boost model performance and evaluation. Develop and implement advanced multi-object tracking algorithms across multiple camera feeds, perform camera calibration, extract regions of interest (ROI), and conduct action recognition using temporal analysis.
We are seeking specialists with hands-on experience in Python, PyTorch, and TensorFlow for CV/ML/DL model development, focusing on object detection, recognition, and action recognition. Proficiency with NVIDIA technologies, MLOps, and edge deployment is essential. Experience in writing complex SQL queries is required, with familiarity in NoSQL or Graph Databases (Neo4j) being advantageous. Knowledge of infrastructure as code tools such as Terraform and Ansible, along with containerization technologies like Docker and orchestration tools like Kubernetes, is also beneficial.
Infosys
IT Consulting