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

ByteDance; San Jose (CA); On-site; USD 68,191 - 97,120; Full time

Benefits offered by this job

Health insurance

Housing allowance

Paid holidays

Job summary

ByteDance seeks a Research Scientist Intern (Security for AI) in San Jose to advance security for large language models. You will design and assess protection mechanisms, publish findings, and collaborate with the Technology team on secure AI deployments.

The internship targets PhD candidates with strong AI fundamentals and coding skills in Python/Go/Java, offering hands‑on experience across cutting‑edge AI security research and product impact.

Qualifications

• Currently pursuing PhD in Computer Science or related discipline.
• Excellent knowledge of theory and practice of LLM and foundation model.
• Strong publication record at conferences (NeurIPS, ICML, ICLR, ACL, EMNLP, etc.).

Responsibilities

• Explore, design, and develop security solutions for LLMs to improve robustness against prompts and data leakage.
• Conduct security risk assessments and provide actionable mitigation recommendations.
• Stay informed about AI risks to ensure security across AI projects.
• Keep up with latest AI technologies and trends to strengthen security of AI products.
• Collaborate with external organizations and experts to advance AI security practices.
• Evaluate and optimize internal AI security processes and frameworks.
• Provide leadership to teams and clients on secure AI adoption.
• Develop and deliver training on secure AI principles and practices.

Skills

LLM theory and practice

Publications in AI/NLP conferences

Programming in Python/Go/Java

Education

PhD candidate in Computer Science

Tools

Python

Go

Java

Job description

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

Location: San Jose

Team: Technology

Employment Type: Intern

Job Code: A180027A

Overview

Nestled Flow AI Organization, the Security AI team stands as a beacon of innovation, exploring cutting‑edge technology to enhance the security of Large Language Models (LLMs) and their applications serving the company’s global products. Tasked with constructing, implementing, and sustaining secure frameworks, the team pioneers a new frontier in AI Security Research, inviting talented individuals with a background in AI to join through the student researcher program. Through collaboration and unwavering commitment, this team ensures a safe and secure digital experience for users worldwide while offering a stimulating environment for LLM enthusiasts to thrive and shape the future of AI security. We are looking for talented individuals to join us for an internship in 2026.

Responsibilities

Job Responsibilities:

• Explore, design, and develop security solutions for Large Language Models (LLMs), such as techniques to enhance LLM robustness against potential threats like prompt injections and private information disclosure.
• Conduct comprehensive security risk assessments and provide actionable recommendations for mitigating potential vulnerabilities in LLMs.
• Stay well‑informed about existing AI risks to ensure the highest level of security across all AI projects.
• Keep abreast of the latest AI technologies and trends, proactively identifying opportunities to strengthen the security of AI products.
• Foster strategic collaborations with external organizations and experts to remain at the forefront of best practices and advancements in AI security.
• Continuously evaluate and optimize internal processes and procedures related to AI security to maintain a robust and resilient framework.
• Provide leadership and guidance to clients, empowering them to understand and adopt secure AI practices seamlessly.
• Develop and deliver comprehensive training and educational programs on secure AI principles and best practices to team members, promoting a culture of AI security awareness and excellence.

Qualifications

Minimum Qualifications:

• Currently pursuing PhD in Computer Science or a related discipline.
• Excellent knowledge of theory and practice of LLM and foundation model.
• Strong publication record at conferences (NeurIPS, ICML, ICLR, ACL, EMNLP, etc.).

Preferred Qualifications:

• Good communication and collaboration skills, able to explore new technologies with the team and promote technological progress.
• Demonstrated software engineering or natural language processing, or deep learning experience from previous internships, work experience, coding competitions, or publications.
• High levels of creativity and quick problem‑solving capabilities.
• Excellent coding ability, familiar with data structures, and fundamental algorithm skills, proficient in Python or Go or Java; winners of competitions such as ACM/ICPC, USACO/NOI/IOI, Top Coder, Kaggle, etc. are preferred.

Job Information

The hourly rate range for this position in the selected city is $60-$60.

Benefits may vary depending on the nature of employment and the country work location. Interns have day one access to health insurance, life insurance, wellbeing benefits and more. Interns also receive 10 paid holidays per year and paid sick time (56 hours if hired in first half of year, 40 if hired in second half of year). Interns who are not working 100% remote may also be eligible for housing allowance.

The Company reserves the right to modify or change these benefits programs at any time, with or without notice.

EEO & Legal Compliance

For Los Angeles County (unincorporated) Candidates: Qualified applicants with arrest or conviction records will be considered for employment in accordance with all federal, state, and local laws including the Los Angeles County Fair Chance Ordinance for Employers and the California Fair Chance Act. Our company believes that criminal history may have a direct, adverse and negative relationship on the following job duties, potentially resulting in the withdrawal of the conditional offer of employment:

1. Interacting and occasionally having unsupervised contact with internal/external clients and/or colleagues;
2. Appropriately handling and managing confidential information including proprietary and trade secret information and access to information technology systems;
3. Exercising sound judgment.

Reasonable Accommodation

ByteDance is committed to providing reasonable accommodations in our recruitment processes for candidates with disabilities, pregnancy, sincerely held religious beliefs or other reasons protected by applicable laws. If you need assistance or a reasonable accommodation, please reach out to us at tinyurl.com/RA-request.