Research Scientist Intern (Security for AI) - 2026 Start (PhD)

ByteDance
San Jose
Workplace: OnsiteInternshipFunction: Data Science & Machine LearningEducation: phdSkills: ["Communication","Collaboration","Creativity","Problem-solving","Leadership"]

Work with ByteDance’s Security AI team to research and build defenses for Large Language Models, focusing on threats like prompt injection and private information disclosure. Conduct security risk assessments, track emerging AI security risks and technologies, and collaborate with external experts. You’ll also help evaluate internal security processes and deliver training to promote secure AI practices across teams.

Loading

Loading job details...

Preparing the role view and application actions.

FursaFursa
ByteDance
ByteDance
1 month ago

Research Scientist Intern (Security for AI) - 2026 Start (PhD)

✓ Verified Job

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

Source: Company careers pageValidated by: Fursa AI
Last checked: 31 days agoStatus: Live
Reposted: similar role first listed 1 month ago

Job Summary

Work with ByteDance’s Security AI team to research and build defenses for Large Language Models, focusing on threats like prompt injection and private information disclosure. Conduct security risk assessments, track emerging AI security risks and technologies, and collaborate with external experts. You’ll also help evaluate internal security processes and deliver training to promote secure AI practices across teams.
Location: San Jose
Workplace: Onsite
Employment Type: Internship
Job Function: Data Science & Machine Learning
Seniority: Intern level

Key Responsibilities

  • •Explore, design, and develop security solutions for LLMs, improving robustness against threats like prompt injection and private information disclosure.
  • •Perform security risk assessments on LLMs and provide actionable recommendations to mitigate vulnerabilities.
  • •Monitor and analyze existing AI risks to help ensure security across AI projects.
  • •Stay current on AI technologies and trends to identify opportunities to strengthen AI product security.
  • •Develop and deliver training on secure AI principles and best practices, and guide teams on adopting secure AI practices.

Key Requirements

  • •Currently pursuing a PhD in Computer Science or a related discipline.
  • •Excellent knowledge of theory and practice of LLMs and foundation models.
  • •Strong publication record at conferences such as NeurIPS, ICML, ICLR, ACL, and EMNLP.
  • •Good communication and collaboration skills to explore new technologies with the team.
  • •Strong coding ability with data structures and algorithms; experience with Python, Go, or Java is preferred.
Experience:AILLMsFoundation modelsNatural language processingDeep learning
Education:PhD / Doctorate in Computer Science or related discipline
Skills:CommunicationCollaborationCreativityProblem-solvingLeadership
Tech Stack:LLMsFoundation modelsPythonGoJavaData structuresAlgorithmsPrompt injectionNatural language processing

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
WebsiteLinkedIn