Senior Computer Vision Engineer

Requirements

Key Responsibilities

• Design, develop, and optimize by fine-tuning diffusion models tailored for furniture detection, replacement, placement in images, and ultra-realistic rendering.
• Create ultra-realistic image re-rendering pipelines for seamless integration of furniture in diverse environments
• Collaborate with product and design teams to understand requirements and deliver impactful AI-powered solutions.
• Research and implement state-of-the-art generative AI techniques for photorealistic image synthesis.
• Train, fine-tune, and deploy models, ensuring high accuracy and performance on large-scale datasets
• Develop scalable APIs and systems to integrate model capabilities into production workflows by working closely with the DevOps Engineer.
  

Requirements

Experience:

• 3-8 years of experience in Generative AI with a focus on diffusion models.
• Solid experience building image generation models using architectures like Variational Autoencoders (VAEs), U-Net and Vision Transformers.
• Good understanding of classical computer vision techniques, and ability to solve 2D vision problems using OpenCV and Open3D
• Practical experience working with 3D computer vision, including handling point clouds, 3D reconstruction, and processing 3D point-cloud data
• Demonstrable experience in furniture or object replacement and re-rendering using generative models. Skills: Strong proficiency in frameworks like PyTorch
• Expertise in fine-tuning diffusion models (e.g., Stable Diffusion, Denoising Diffusion Probabilistic Models).
• Expertise in distributed training using CUDA-enabled GPUs
• Solid knowledge of GANs, NeRF, or other generative models for realistic image synthesis.
• Familiarity with 3D rendering pipelines, textures, and lighting models.
• Proficiency in creating and working with large image-based datasets and optimizing model performance.
  

Soft Skills:

• Strong analytical and problem-solving skills.
• Excellent communication and ability to explain complex ideas and model architectures clearly.
• A proactive and collaborative mindset for teamwork