AI ENGINEER
Summary
Develops and fine-tunes vision generative models (e.g., Diffusion Models) and multimodal models for real-world products like manga/story generation using PyTorch/TensorFlow.
Responsibilities
Conduct research and development in computer vision, with emphasis on training and fine-tuning vision generative models (e.g., Diffusion Models) and large multimodal models
Apply cutting-edge AIGC technologies to real-world product scenarios, and participate in innovative projects such as multimodal manga/story generation
Collaborate with cross-functional teams to drive end-to-end model delivery (including deployment and optimization), solving practical business challenges
Write technical documentation, patents, and academic papers
Qualifications
Master's degree or above in Computer Vision, Deep Learning, or related fields, with over 2 years of relevant work experience
Proficient in Python, with hands-on experience in deep learning frameworks such as PyTorch and TensorFlow
Experience with generative models, including Diffusion Models, multimodal model fine-tuning (e.g., LoRA), and image-to-image generation
Proven ability to apply deep learning technologies to real-world products; passionate about emerging technologies, capable of tackling challenging problems and quickly validating solutions
Solid research track record, with at least one first-authored publication at international conferences such as ICIP, NeurIPS, WACV, or FG