Computer Vision Architect / Lead

Infosys; Bengaluru; On-site; INR 1,200,000 - 1,800,000; Full time

Job summary

Infosys is seeking a Computer Vision Architect/Lead to design, train, and optimize deep learning models for object detection, image recognition, segmentation, and video analytics. You will lead real-time deployments across 100+ video streams, and collaborate with teams to deliver scalable CV solutions.

Responsibilities include fine-tuning CNNs and Vision Transformers with TensorFlow, PyTorch, and ONNX; building inference pipelines with NVIDIA tools; and implementing robust post-processing, ROI

Qualifications

• Lead real-time computer vision deployments across 100+ video streams.
• Fine-tune CNNs and Vision Transformers with TensorFlow, PyTorch, and ONNX.
• Develop inference pipelines using NVIDIA tools such as TAO Toolkit, DeepStream, and Triton Server.
• Apply pre- and post-processing to boost model performance.
• Develop and implement multi-object tracking across camera feeds.
• Perform camera calibration and ROI extraction, plus action recognition via temporal analysis.
• Develop feature extraction models and conduct latent space analysis.

Responsibilities

• Lead large-scale real-time implementations involving 100+ video streams.
• Fine-tune models like CNNs and Vision Transformers using TensorFlow, PyTorch, and ONNX.
• Build and deploy inference pipelines using NVIDIA technologies including NGC models, TAO Toolkit, DeepStream Metropolis, and Triton Server.
• Apply pre- and post-processing techniques to enhance model performance and evaluation.
• Develop and implement multi-object tracking algorithms across multiple camera feeds.
• Perform camera calibration and extract regions of interest (ROI), action recognition using temporal analysis techniques.
• Develop models for feature extraction and come up with strategies for latent space analysis and manipulation of the data.
• Proficiency in writing complex SQL queries; familiarity with NoSQL or Graph Databases (Neo4j) is an advantage.
• Knowledge of infrastructure as code tools (Terraform, Ansible) is an advantage.
• Proficiency with containerization (Docker) and orchestration (Kubernetes) is an advantage.

Skills

Computer Vision

Deep Learning

Object Detection

Image Recognition

Video Analytics

Real-time Systems

CNNs

Vision Transformers

Model Fine-tuning

SQL

NoSQL

Graph Databases

Latent Space Analysis

ROI Extraction

Tools

TensorFlow

PyTorch

ONNX

NVIDIA TAO Toolkit

NVIDIA DeepStream

Triton Server

Docker

Kubernetes

Terraform

Ansible

Neo4j

Job description

Computer Vision Architect/ Lead Design, train, and optimize deep learning models for computer vision tasks such as object detection, image recognition, segmentation, and video analytics.

• Lead large-scale real-time implementations involving 100+ video streams.
• Fine-tune models like CNNs and Vision Transformers using frameworks such as TensorFlow, PyTorch, and ONNX.
• Build and deploy inference pipelines using NVIDIA technologies including NGC models, TAO Toolkit, DeepStream Metropolis, and Triton Server.
• Apply pre- and post-processing techniques to enhance model performance and evaluation.
• Develop and implement multi-object tracking algorithms across multiple camera feeds., Perform camera calibration and extract regions of interest (ROI), action recognition using temporal analysis techniques.
• Develop models for feature extraction and come up with strategies for latent space analysis and manipulation of the data.
• Proficiency in writing complex SQL queries, familiarity with NoSQL or Graph Databases (Neo4j) is an advantage.
• Knowledge of infrastructure as code tools (e.g., Terraform, Ansible) is an advantage.
• Proficiency with containerization technologies (Docker) and orchestration tools (Kubernetes) is an advantage.