Computer Vision Expert

We are looking for a Computer Vision Engineer / Expert with 3–4 years of proven professional experience in developing and deploying real-world Computer Vision and AI solutions. The ideal candidate should have strong hands-on experience with Python, PyTorch, OpenCV, Computer Vision, Deep Learning, image processing, segmentation, and real-time AI systems. Experience in Human Parsing, Virtual Try-On, 3D Human Reconstruction, and Generative AI will be highly preferred.

Key Responsibilities :

• Develop and deploy Computer Vision and Deep Learning solutions.
• Work on image/video processing, object detection, segmentation, classification, and pose estimation.
• Develop Human Parsing and Body Segmentation solutions.
• Build and optimize real-time Computer Vision applications.
• Train, fine-tune, test, and evaluate AI/CV models.
• Create, clean, annotate, and manage Computer Vision datasets.
• Optimize models for GPU inference, performance, and low latency.
• Deploy AI/CV models in production and cloud environments.
• Integrate Computer Vision models into software products and applications.
• Research and implement modern Computer Vision and AI techniques.

Requirements :

• 3–4 Years of Proven Professional Experience in Computer Vision / AI.
• Strong hands-on experience with Python, PyTorch, OpenCV, and NumPy.
• Strong Computer Vision and Deep Learning fundamentals.
• Practical experience with image segmentation, object detection, classification, and pose estimation.
• Experience with real-world Computer Vision projects and production deployment.
• Experience with real-time/video-based Computer Vision is preferred.
• Knowledge of ONNX, TensorRT, CUDA, and GPU inference.
• Experience with Linux, Git, Docker, and REST APIs.
• Experience with dataset creation, annotation, and preprocessing.
• Human Parsing / Body Segmentation.
• Virtual Try-On (VTON/VITON).
• Diffusion Models, Stable Diffusion, Inpainting, and ControlNet.
• SMPL / SMPL-X and 3D Human Body Reconstruction.
• Depth Maps, Point Clouds, Meshes, and 3D Vision.
• Open3D, PyTorch3D, Trimesh, or Blender.
• C++, FastAPI, AWS/GCP GPU infrastructure.

Work Location: In person