多模态算法工程师-豆包手机助手
Core
Develop and optimize multimodal large models (VLM, Diffusion) for camera and photo album features, including shooting guidance, aesthetic analysis, and image editing agents.
Role type
Senior IC multimodal algorithm engineer (VLM/Diffusion)
Builds
Multimodal large models and camera/photo album product features
Domain
Consumer technology, Computer Vision, Generative AI
Deliverable
production ML models
Required skills
VLM development, Diffusion model development, architecture design, data construction, pre-training, post-training, computer vision algorithms
Preferred skills
Camera/album algorithm experience, publications in CVPR/ICCV/NeurIPS/ICML/ICLR
Technologies
VLM, Diffusion models
Sourced via bytedance · Listed on CareerPlan, which tracks 844,000+ jobs from 20+ sources.
