Visual Generation & Multimodal Evaluation Researcher Graduate

About the Role

ByteDance's Applied Machine Learning Ark team focuses on developing and operating Large Language Model (LLM) service platforms, offering Model-as-a-Service (MaaS) solutions. The US team is responsible for the design, development, and operation of MaaS solutions for US and international markets outside mainland China. This involves building full-stack, end-to-end solutions for text and multimodal LLMs, including training/fine-tuning/inference frameworks, prompt engineering, model alignment, and intelligent agent systems. The team also operates large-scale log analytics pipelines for insights and model improvement.

Key Responsibilities

• Build evaluation systems for image and video models/agents, covering generation quality, instruction following, multimodal understanding, and safety.
• Develop automated metrics and model-based evaluators, and design reproducible human evaluation protocols.
• Design and develop video generation/debugging agents that orchestrate multi-step creative workflows.
• Build large-scale image and video data pipelines, and translate evaluation findings into model and product improvements.

Requirements & Tech Stack

• Minimum Qualifications:
• Individuals who are completing or have recently completed a PhD's degree in Computer Science, Artificial Intelligence, Machine Learning, Computer Vision, or a related field.
• Solid foundation in deep learning and computer vision, including generative modeling fundamentals.
• Practical experience in at least one of: visual generation, multimodal LLMs, video understanding, or visual quality assessment.
• Strong Python skills and proficiency with PyTorch or an equivalent framework, or multimodal evaluation framework.
• Demonstrated research or engineering ability through publications, substantial projects, internships, or open-source work.
• Preferred Qualifications:
• Publications at top-tier vision or ML venues (e.g., NeurIPS, ICML, CVPR, ICCV, ECCV).
• Hands-on experience with modern visual generation stacks, including diffusion-based models and their post-training.
• Familiarity with visual generation benchmarks, or experience building evaluation frameworks.
• Experience applying agent frameworks to creative workflows, or working with large-scale video data infrastructure.

Qualifications

• Individuals who are completing or have recently completed a PhD's degree in Computer Science, Artificial Intelligence, Machine Learning, Computer Vision, or a related field.
• Solid foundation in deep learning and computer vision, including generative modeling fundamentals.
• Practical experience in at least one of: visual generation, multimodal LLMs, video understanding, or visual quality assessment.
• Strong Python skills and proficiency with PyTorch or an equivalent framework, or multimodal evaluation framework.
• Demonstrated research or engineering ability through publications, substantial projects, internships, or open-source work.
• Publications at top-tier vision or ML venues are preferred.
• Hands-on experience with modern visual generation stacks, including diffusion-based models and their post-training, is preferred.
• Familiarity with visual generation benchmarks, or experience building evaluation frameworks, is preferred.
• Experience applying agent frameworks to creative workflows, or working with large-scale video data infrastructure, is preferred.