Computer Vision AI Developer

Sahana System Limited; Ahmedabad District; Hybrid; INR 1,200,000 - 2,400,000; Full time

Benefits offered by this job

Competitive compensation

Mentorship & learning

Cross-functional teams in Ahmedabad

Hybrid work option

Job summary

Sahana System Limited in Ahmedabad is seeking experienced Computer Vision AI Developers to design, develop, optimize, and deploy CV models and pipelines for real-world applications.

The role covers data prep, model training, deployment, and production integration with APIs and microservices, with on-site or hybrid work based on project needs. Strong Python, DL fundamentals, and CV libraries are essential.

Qualifications

• Bachelors or masters in CS/EC/DS/AI/ML or related field.
• Strong Python programming; C++ knowledge is a plus.
• Hands-on with CV libraries and frameworks (PyTorch/TensorFlow/Keras, OpenCV).
• Solid DL fundamentals, CNNs, and image processing techniques.
• Experience with Docker, Flask/FastAPI, ONNX, TensorRT or equivalent.
• Familiarity with AWS/Azure/GCP and edge deployments (Jetson/RPi).
• Experience with CVAT/LabelImg/Labelbox and dataset management.
• Git and collaborative software development workflows.

Responsibilities

• Design, develop, and fine-tune CV models for detection, classification, segmentation, and OCR.
• Build end-to-end CV pipelines including data prep, augmentation, and training.
• Optimize models for accuracy, latency, and resource use across cloud/edge/embedded.
• Collaborate with data engineering and product teams to productionize models via APIs.
• Perform model evaluation, error analysis, and performance monitoring.
• Deploy and manage models with MLOps, including versioning, Docker, and CI/CD.
• Document designs, experiments, and results; share knowledge and best practices.
• Stay updated on CV, DL, and Generative AI advances and assess relevance for projects.

Skills

Python

C++

Computer Vision

Deep Learning

Model Deployment

Docker

FastAPI

PyTorch

TensorFlow

OpenCV

Git

AWS/Azure/GCP

NVIDIA Jetson/Raspberry Pi

Education

Bachelor's or Master's in CS/EC/DS/AI/ML

Tools

Docker

Flask/FastAPI

ONNX

TensorRT

PyTorch

TensorFlow

Keras

OpenCV

Git

AWS/Azure/GCP

NVIDIA Jetson/Raspberry Pi

Job description

Work Mode: On-site / Hybrid, based on project requirements

Department: Technology Delivery / AI & Computer Vision

Position Overview

We are looking for experienced Computer Vision AI Developers to design, develop, optimize, and deploy computer vision models and pipelines for real-world applications. The role involves working across the complete CV lifecycle, from data preparation and model development to optimization and production deployment.

Key Responsibilities

• Design, develop, and fine-tune Computer Vision models for object detection, image classification, segmentation, tracking, and OCR.
• Build and maintain end-to-end Computer Vision pipelines, including data ingestion, preprocessing, augmentation, annotation, and model training.
• Optimize models for accuracy, latency, and resource efficiency for cloud, edge, and embedded deployments.
• Work with PyTorch, TensorFlow, Keras, and OpenCV, implementing architectures such as CNNs, YOLO, Faster R-CNN, ViT, and U-Net.
• Collaborate with data engineering and product teams to integrate Computer Vision models into production applications, APIs, and microservices.
• Perform model evaluation, error analysis, and performance monitoring, and continuously improve models based on real-world feedback.
• Deploy and manage models using MLOps practices, including model versioning, Docker, and CI/CD pipelines.
• Document technical designs, experiments, and results while contributing to knowledge sharing and engineering best practices.
• Stay updated with advancements in Computer Vision, Deep Learning, and Generative AI, and evaluate their applicability to client projects.

Required Qualifications & Skills

• Bachelors or masters degree in computer science, Electronics, Data Science, AI/ML, or a related field.
• Strong programming skills in Python; working knowledge of C++ is an advantage.
• Hands-on experience with Computer Vision libraries and frameworks, including:
• Strong understanding of Deep Learning fundamentals, CNN architectures, and image processing techniques.
• Experience with model deployment tools such as Docker, Flask/FastAPI, ONNX, TensorRT, or similar technologies.
• Familiarity with AWS, Azure, or GCP and/or edge deployment platforms such as NVIDIA Jetson or Raspberry Pi.
• Experience with data annotation tools such as CVAT, LabelImg, or Labelbox, along with dataset management.
• Working knowledge of Git and collaborative software development workflows.
• Strong analytical and problem-solving skills, with the ability to work independently and effectively within a team.

Good To Have:

• Exposure to Video Analytics, Multi-Object Tracking, or 3D Vision, including depth estimation and point clouds.
• Experience with Generative AI and Vision-Language Models, such as diffusion models, CLIP, or multimodal LLMs.
• Prior experience in domains such as manufacturing, surveillance/security, retail, healthcare imaging, or defence technology.
• Familiarity with MLOps tools such as MLflow, Kubeflow, or Airflow.
• Publications, open-source contributions, or Kaggle experience in Computer Vision.

What We Offer:

• Opportunity to work on diverse, high-impact Computer Vision projects across multiple industry verticals.
• A dedicated and growing AI/CV practice with access to structured learning and mentorship.
• Competitive compensation aligned with experience and market benchmarks.
• Collaborative work culture in Ahmedabad, with exposure to cross-functional teams across Sahana's Enterprise and MSI business units.