Computer Vision Expert

We are seeking a Computer Vision Engineer with 3 to 4 years of proven professional experience in developing and deploying real-world Computer Vision and AI solutions. The ideal candidate will have strong hands-on expertise in Python, PyTorch, OpenCV, and deep learning frameworks, with a solid background in image processing, segmentation, and real-time AI systems. Experience working on advanced topics such as Human Parsing, Virtual Try-On, 3D Human Reconstruction, and Generative AI is highly desirable.

Key Responsibilities:
- Develop and deploy Computer Vision and Deep Learning solutions tailored to real-world applications.
- Work extensively on image and video processing tasks including object detection, segmentation, classification, and pose estimation.
- Design and implement Human Parsing and Body Segmentation algorithms.
- Build and optimize real-time Computer Vision applications ensuring high performance and low latency.
- Train, fine-tune, test, and evaluate AI and Computer Vision models to meet project requirements.
- Create, clean, annotate, and manage datasets specific to Computer Vision projects.
- Optimize models for GPU inference using tools such as ONNX, TensorRT, and CUDA.
- Deploy AI and Computer Vision models in production environments, including cloud platforms.
- Integrate Computer Vision models into existing software products and applications.
- Conduct research and implement state-of-the-art Computer Vision and AI techniques to enhance product capabilities.

Required Qualifications:
- 3 to 4 years of professional experience in Computer Vision and AI development.
- Strong proficiency in Python, PyTorch, OpenCV, and NumPy.
- Solid understanding of Computer Vision and Deep Learning fundamentals.
- Practical experience with image segmentation, object detection, classification, and pose estimation.
- Proven track record of working on real-world Computer Vision projects and deploying models in production.
- Familiarity with real-time and video-based Computer Vision applications.
- Knowledge of GPU inference optimization tools such as ONNX, TensorRT, and CUDA.
- Experience working with Linux, Git, Docker, and REST APIs.
- Skilled in dataset creation, annotation, and preprocessing for Computer Vision tasks.

Preferred Qualifications and Additional Expertise:
- Experience with Human Parsing and Body Segmentation techniques.
- Familiarity with Virtual Try-On technologies (VTON/VITON).
- Knowledge of Diffusion Models, Stable Diffusion, Inpainting, and ControlNet.
- Expertise in SMPL/SMPL-X models and 3D Human Body Reconstruction.
- Understanding of depth maps, point clouds, meshes, and 3D vision processing.
- Experience with 3D libraries and tools such as Open3D, PyTorch3D, Trimesh, or Blender.
- Programming skills in C++ and experience with FastAPI.
- Exposure to cloud GPU infrastructure such as AWS or GCP.

This position requires working on-site to collaborate closely with the team and contribute effectively to ongoing projects. If you are passionate about pushing the boundaries of Computer Vision and AI technologies and meet the above criteria, we encourage you to apply.