Senior AI Engineer / Computer Vision Expert

We are looking for an AI Engineer / Computer Vision Expert with strong hands-on experience in Computer Vision, Human Parsing, Virtual Try-On, Diffusion Models, 3D Human Body Reconstruction, and real-time AI deployment with at least 3-4 Years of Proven Professional Experience.

The ideal candidate should have experience developing and deploying real-world AI/CV products, working with PyTorch, OpenCV, Python, GPU inference, and modern CV/Generative AI models. Experience with VTON, SMPL/SMPL-X, 3D vision, ONNX/TensorRT, and dataset development will be highly valuable.

(Please review the Job Description and Requirements carefully before submitting your application.)

Job Description (JD):

• Develop and implement Computer Vision and AI solutions.
• Work on Human Parsing and Body Segmentation systems.
• Develop or integrate Virtual Try-On (VTON) solutions.
• Work with diffusion-based image generation and image-to-image models.
• Work with 3D human body reconstruction and body measurement technologies.
• Develop real-time Computer Vision applications for cameras/mirror/kiosk systems.
• Train, fine-tune, and evaluate AI/CV models.
• Create, clean, annotate, and manage Computer Vision datasets.
• Deploy AI models on GPU/cloud/production environments.
• Optimize models for real-time inference and lower latency.
• Work with Python, PyTorch, OpenCV, NumPy, and related frameworks.
• Collaborate with the product and engineering team to convert AI concepts into working products.

Job Requirements (JR):

• Strong hands-on experience in Python, PyTorch, OpenCV, and NumPy.
• At least 3-4 Years of Proven Professional Experience is Required for this Role.
• Strong Computer Vision background with real-world project experience.
• Experience with human parsing, segmentation, and pose estimation.
• Experience with VITON/VTON or similar virtual try-on technologies.
• Understanding of Diffusion Models, Stable Diffusion, Inpainting, and ControlNet.
• Experience with SMPL/SMPL-X or 3D human reconstruction is highly preferred.
• Understanding of depth maps, point clouds, meshes, and 3D reconstruction.
• Experience with model deployment and production AI systems.
• Knowledge of ONNX, TensorRT, CUDA, and GPU inference.
• Experience with Docker, Linux, Git, and REST APIs.
• Experience with dataset creation, annotation, and quality control.
• Experience with real-time/video-based Computer Vision is preferred.
• Knowledge of Open3D, PyTorch3D, Trimesh, or Blender APIs is a plus.
• C++, FastAPI, and AWS/GCP GPU infrastructure experience is a plus.
• Ability to explain previous projects and demonstrate actual hands-on contribution.

Pay: Rs140,000.00 - Rs250,000.00 per month

Work Location: In person