Flag job

Report

Senior Computer Vision Engineer

Location

Ahmedabad, Gujarat, India

JobType

full-time

About the job

Info This job is sourced from a job board

About the role

Aerocraft Engineering

Website: aerocraftengineering.com
Job details:
About the job


About Our Company:

Aerocraft Engineering India Pvt Ltd based in Ahmedabad, provides services to US-based Architecture, Engineering, and Construction groups of companies:

  • Russell and Dawson – An Architecture/Engineering/Construction firm (www.rdaep.com)
  • United-BIM – BIM Modeling Services Firm (www.united-bim.com)
  • AORBIS – Procurement as a Service Provider (www.aorbis.com)


We are a nimble and growing organization where everyone’s role is very important for the company’s business success. All team members’ contributions have a direct correlation with the company’s performance in meeting its business and financial objectives.


We are seeking a talented Computer Vision Engineer with 5+ years of hands-on experience to join our innovative team. The ideal candidate will have strong expertise in computer vision algorithms, image processing, and 3D reconstruction techniques. You will be responsible for developing and implementing cutting-edge computer vision solutions that drive our products forward.


Experience Required - Minimum 5+ Years


Job Location:

  • Ahmedabad (Siddhivinayak Towers, Makarba)


Shift Timings:

  • 11am to 8pm/ 9am to 6pm (Shift may change as per business requirement)
  • Monday to Friday
  • Work from office


Key Responsibilities

Core Development

  • Design, develop, and optimize computer vision algorithms for real-time applications
  • Implement robust object detection, tracking, and recognition systems
  • Develop 3D reconstruction and depth estimation solutions from 2D images.
  • Create and maintain wireframe generation algorithms for architectural and structural analysis
  • Build end-to-end computer vision pipelines from data acquisition to deployment

Technical Implementation

  • Optimize algorithms for performance on edge devices and cloud platforms
  • Integrate computer vision solutions with existing software systems and APIs
  • Develop prototypes and proof-of-concepts for new computer vision applications
  • Implement data augmentation strategies and synthetic data generation techniques

Research & Innovation

  • Stay current with latest research papers and advancements in computer vision
  • Evaluate and benchmark different algorithms and model architectures
  • Contribute to patent applications and technical publications
  • Collaborate with research teams to translate cutting-edge research into production

Quality & Testing

  • Design and implement comprehensive testing strategies for vision systems
  • Perform accuracy assessment and error analysis of vision algorithms
  • Create validation datasets and ground truth annotations
  • Debug and troubleshoot complex computer vision issues

Required Technical Skills

Core Computer Vision

  • Minimum 5 years of hands-on experience with OpenCV (Python/C++)
  • Strong expertise in Object Detection frameworks:
  • YOLO (v5/v7/v8/v11)
  • Faster R-CNN, Mask R-CNN
  • SSD, RetinaNet
  • Experience with custom object detector training
  • Proficiency in 3D Computer Vision:
  • 3D reconstruction from multiple views
  • Structure from Motion (SfM)
  • Stereo vision and depth estimation
  • Point cloud processing (PCL, Open3D)
  • Experience with Wireframe Detection and Generation:
  • Edge detection and line segment detection
  • Structural analysis from images
  • CAD model generation from images
  • Building/architectural wireframe extraction

Machine Learning & Deep Learning

  • Strong foundation in CNNs, RNNs, and Transformer architectures
  • Experience with deep learning frameworks:
  • PyTorch (preferred) or TensorFlow
  • ONNX for model deployment
  • TensorRT for optimization
  • Knowledge of semantic segmentation and instance segmentation
  • Experience with GANs for image generation/enhancement

Programming & Tools

  • Languages: Proficient in Python, C++ (OpenCV implementations)
  • Libraries: NumPy, scikit-image, PIL/Pillow, matplotlib
  • Development Tools: Git, Docker, Linux environment
  • Cloud Platforms: Experience with AWS/Azure/GCP for ML deployment
  • GPU Programming: CUDA programming is a plus

Additional Technical Areas

  • Image preprocessing and enhancement techniques
  • Feature extraction and matching (SIFT, SURF, ORB)
  • Optical flow and motion estimation
  • Video analytics and real-time processing
  • Experience with AR/VR applications
  • Knowledge of photogrammetry techniques


Click on Apply to know more.

Skills

Python
Azure
C++
CAD
computer vision
CUDA
deep learning
Docker
end-to-end
GCP
Git
GPU
Linux
machine learning
Matplotlib
NumPy
point cloud processing
prototypes
TensorFlow
wireframe
Pytorch
ONNX