Position Overview:

We are seeking a AI Engineer focused on Generative AI Image and Video Algorithm Development. The ideal candidate should have experience in developing and optimizing generative AI algorithms, including but not limited to Stable Diffusion (image or video), GANs, ControlNet, and LoRA. In particular, expertise is required in portrait generation, 3D depth-aware scenes, and image inpainting, designing efficient generative AI models to address challenges related to image realism, consistency, and harmony, thereby improving overall image quality and optimizing the visual experience.

Responsibilities:

• Research and develop advanced generative AI algorithms for image quality enhancement, focusing on clarity, color consistency, and noise reduction;
• Research and develop advanced generative AI image quality algorithms to enhance image clarity, realism, consistency, and visual harmony.
• Optimize image generation and rendering quality in portrait and depth-aware scenes, aligning with product application workflows.
• Improve image quality and novel view synthesis in complex depth scenarios, including small objects, motion scenes, and stereo vision.
• Participate in the full algorithm development lifecycle, from prototyping to product deployment, collaborating closely with software and hardware engineering teams to ensure efficient algorithm integration.

Qualification/ Requirements:

• Master's or Ph.D. degree in Computer Vision, Image Processing, Large Models, or related fields.
• Proven experience in research and development of generative AI image generation algorithms, with proficiency in Stable Diffusion, GANs, ControlNet, LoRA, and model optimization.
• Familiarity with novel view synthesis, depth image generation, and image inpainting models, along with efficient training and data preparation pipelines.
• Proficiency in Python, with experience in PyTorch or other deep learning frameworks.
• Strong capability in developing and optimizing generative AI algorithms to enhance image quality in terms of clarity, realism, consistency, and harmony.
• Prior experience in image generation system development and optimization is a plus, including but not limited to text-to-image generation, conditional generation, image editing, style transfer, image inpainting, super-resolution, and image enhancement.
• Excellent teamwork, communication, and problem-solving skills.

Required Skills:

• Programming Languages: Python

• Deep Learning Frameworks:PyTorch, TensorFlow

• Image Processing Libraries:OpenCV, PIL/Pillow, scikit-image

• Generative AI Techniques:GANs, VAEs, Stable Diffusion, ControlNet

• Version Control & Collaboration:Git, GitHub/GitLab, Docker

• Language Skills: Proficient in English with strong reading and communication abilities