Applied Research Intern- AI Safety Security -Global Tech Research Program-2027 Start (PhD)

ByteDance
San Jose
Workplace: OnsiteInternshipFunction: Research & Scientific (R&D)Education: phdSkills: ["Communication","Collaboration","Creativity","Problem-solving"]

Join the Security AI team to research and evaluate AI safety for agent-based and foundation-model systems. You’ll work on adversarial testing and defense techniques, build benchmarks and toolchains, and explore trustworthy runtime security and secure training/inference for protecting data and model assets. The internship emphasizes hands-on research, collaboration with industry experts, and strong publication and coding expectations.

Loading

Loading job details...

Preparing the role view and application actions.

FursaFursa
ByteDance
ByteDance
1 month ago

Applied Research Intern- AI Safety Security -Global Tech Research Program-2027 Start (PhD)

✓ Verified Job

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

Source: Company careers pageValidated by: Fursa AI
Last checked: 30 days agoStatus: Live
Reposted: similar role first listed 1 month ago

Job Summary

Join the Security AI team to research and evaluate AI safety for agent-based and foundation-model systems. You’ll work on adversarial testing and defense techniques, build benchmarks and toolchains, and explore trustworthy runtime security and secure training/inference for protecting data and model assets. The internship emphasizes hands-on research, collaboration with industry experts, and strong publication and coding expectations.
Location: San Jose
Workplace: Onsite
Employment Type: Internship
Job Function: Research & Scientific (R&D)
Seniority: Intern level

Key Responsibilities

  • •Research adversarial testing and evaluation technologies for foundation models and agents in the agentic AI era.
  • •Develop attack-defense detection and evaluation methods, benchmarks, and toolchains for multimodal foundation models and agents.
  • •Investigate risk defense technologies and trustworthy runtime security assurance for agent-based applications.
  • •Study training and inference technologies to ensure data and model asset security.
  • •Contribute to secure construction and performance optimization for confidential training and inference infrastructure for foundation models.

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 leading conferences (NeurIPS, ICML, ICLR, ACL, EMNLP, etc.).
  • •Excellent coding ability with data structures and fundamental algorithms; proficient in Python, Go, or Java.
  • •Demonstrated software engineering or NLP/deep learning experience via internships, work, coding competitions, or publications.
Education:PhD / Doctorate in Computer Science
Skills:CommunicationCollaborationCreativityProblem-solving
Tech Stack:PythonGoJavaLLMsFoundation models

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