Vision AI Research Scientist - Generative & Multimodal

ByteDance; San Jose (CA); On-site; USD 218,000 - 388,000; Full time

Benefits offered by this job

Medical insurance

Dental insurance

Vision insurance

401(k) match

Parental leave

Disability insurance

Life insurance

Wellbeing benefits

Paid holidays

Paid sick days

Personal time off

Job summary

ByteDance’s Vision-Applied Research team is seeking a Research Scientist to advance computer vision and generative AI with real-world impact across ByteDance products. You will conduct cutting-edge research, develop novel algorithms, and help bring AI-powered creative tools to life for millions of users.

The role requires 2+ years in CV-related research, strong C/C++ and Python skills, and a track record in generative models or multimodal understanding.

Qualifications

• 2+ years of research and practical experience in computer vision topics including generative models, diffusion models, GANs, image/video synthesis/manipulation/editing, image/video understanding, multimodality, vision and language, generative humans, neural motion synthesis, and human modeling (2D/3D pose estimation, hand pose estimation, human shape estimation), facial analysis.
• Strong coding skills in C/C++ and Python.

Responsibilities

• Conduct cutting-edge research and development in computer vision, generative AI and related fields.
• Transfer advanced technologies to ByteDance products.
• Explore new products with AI technology at its core.

Skills

Computer vision

Generative AI

Diffusion models

GAN

Image/video synthesis

Image/video understanding

Multimodal understanding

Vision & language

2D/3D pose estimation

Hand pose estimation

Human modeling

Facial analysis

C/C++

Python

Tools

C/C++

Python

Job description

ByteDance’s Vision-Applied Research team is seeking a Research Scientist to advance computer vision and generative AI with real-world impact across ByteDance products. You will conduct cutting-edge research, develop novel algorithms, and help bring AI-powered creative tools to life for millions of users.

The role requires 2+ years in CV-related research, strong C/C++ and Python skills, and a track record in generative models or multimodal understanding.