企业微信-多模态算法工程师-文生图方向
Core
Develop and optimize algorithms for text-to-image and image-to-image generation within multimodal large models to enhance quality, controllability, and speed.
Role type
Senior IC multimodal machine learning engineer (text-to-image)
Builds
AIGC features for enterprise WeChat products
Domain
Generative AI, Diffusion Models, Multimodal
Deliverable
production ML models
Required skills
Deep learning, PyTorch, Diffusion Models, Transformer architectures, ControlNet, LoRA, Text Inversion, Python, Data structures and algorithms
Preferred skills
Experience with autoregressive models, model inference acceleration, engineering deployment
Technologies
PyTorch, ControlNet, LoRA, Text Inversion
Responsibilities
Research and optimize text-to-image and image-to-image generation algorithms; Track and implement latest AIGC and diffusion model technologies; Develop controllable generation features like ID consistency and style transfer; Collaborate on model inference acceleration and deployment.
Seniority
Senior, hands-on IC
