ByteDance

2 days ago

Research Scientist Project Intern (Multimodal Interaction & World Model) - 2026 Start (PhD)

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI

Last checked: 32 minutes agoStatus: Live

Job Summary

Join the Multimodal Interaction & World Model team to research and develop multimodal intelligence for virtual/real-world interaction. You’ll work on large-scale multimodal understanding and generation, data construction and fine-tuning, evaluation systems, and advanced world-model capabilities like multimodal RAG, visual CoT, and agents for GUI/games and virtual worlds. This is a short-term project internship requiring at least 3 months commitment.

Location: Singapore

Workplace: Onsite

Employment Type: Internship

Job Function: Data Science & Machine Learning

Seniority: Intern level

Key Responsibilities

•Research multimodal understanding, generative modeling, machine learning, reinforcement learning, AIGC, computer vision, and related AI technologies.
•Work on basic multimodal understanding/generation models, including extreme system optimization, data construction, instruction fine-tuning, preference alignment, and model optimization.
•Improve data synthesis, scalable oversight, model reasoning and planning, and build evaluation systems to assess large-model capabilities.
•Explore advanced multimodal and world-model capabilities such as multimodal RAG, visual CoT, and agent-based systems for GUI/games and virtual worlds.
•Use pre-training, simulation, and other techniques to model environments in virtual/real worlds and enable multimodal interactive exploration and new AI-driven product development.

Key Requirements

•PhD degree in computer, electronics, mathematics, or related majors.
•In-depth research in areas such as computer vision, multimodal, AIGC, machine learning, or rendering generation.
•Excellent analytical and problem-solving skills, including ability to tackle large-model training and application problems independently.
•Good communication and collaboration skills; proactive and able to work harmoniously with the team.

Education:PhD / Doctorate in computer, electronics, mathematics (or related majors)

Skills:Analytical thinkingProblem-solvingCommunicationCollaborationIndependent exploration

Tech Stack:Multimodal understandingGenerationMachine learningReinforcement learningAIGCComputer visionLarge modelsMultimodal RAGVisual CoTAgentsPre-trainingSimulationData constructionInstruction fine-tuningPreference alignmentModel optimizationPythonC/C++

Company Brief

ByteDance

Develops consumer internet and content platforms, including TikTok and other apps for short-form video, news, and entertainment. It also builds advertising, commerce, and creator tools that connect audiences, brands, and publishers across global markets.

Industry: Digital Media

Company Size: Enterprise (1,001+ employees)

Revenue: USD 1B+

Growth: Established Company

Headquarters: Beijing, China

Founded: 2012

Website LinkedIn

Loading job details...

Preparing the role view and application actions.

ByteDance

2 days ago

Research Scientist Project Intern (Multimodal Interaction & World Model) - 2026 Start (PhD)

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI

Last checked: 32 minutes agoStatus: Live

Job Summary

Location: Singapore

Workplace: Onsite

Employment Type: Internship

Job Function: Data Science & Machine Learning

Seniority: Intern level

Key Responsibilities

•Research multimodal understanding, generative modeling, machine learning, reinforcement learning, AIGC, computer vision, and related AI technologies.
•Work on basic multimodal understanding/generation models, including extreme system optimization, data construction, instruction fine-tuning, preference alignment, and model optimization.
•Improve data synthesis, scalable oversight, model reasoning and planning, and build evaluation systems to assess large-model capabilities.
•Explore advanced multimodal and world-model capabilities such as multimodal RAG, visual CoT, and agent-based systems for GUI/games and virtual worlds.
•Use pre-training, simulation, and other techniques to model environments in virtual/real worlds and enable multimodal interactive exploration and new AI-driven product development.

Key Requirements

•PhD degree in computer, electronics, mathematics, or related majors.
•In-depth research in areas such as computer vision, multimodal, AIGC, machine learning, or rendering generation.
•Excellent analytical and problem-solving skills, including ability to tackle large-model training and application problems independently.
•Good communication and collaboration skills; proactive and able to work harmoniously with the team.

Education:PhD / Doctorate in computer, electronics, mathematics (or related majors)

Skills:Analytical thinkingProblem-solvingCommunicationCollaborationIndependent exploration

Company Brief

ByteDance

Industry: Digital Media

Company Size: Enterprise (1,001+ employees)

Revenue: USD 1B+

Growth: Established Company

Headquarters: Beijing, China

Founded: 2012

Website LinkedIn