LLM Research Engineer Intern (Code Optimization and AI-Driven Content Moderation)-2025 Start

TikTok is the leading destination for short-form mobile video. At TikTok, our mission is to inspire creativity and bring joy. TikTok's global headquarters are in Los Angeles and Singapore, and its offices include New York, London, Dublin, Paris, Berlin, Dubai, Jakarta, Seoul, and Tokyo.

Why Join Us
Creation is the core of TikTok's purpose. Our platform is built to help imagination thrive. This is doubly true of the teams that make TikTok possible.
Together, we inspire creativity and bring joy - a mission we all believe in and aim towards achieving every day.
To us, every challenge, no matter how difficult, is an opportunity; to learn, to innovate, and to grow as one team. Status quo? Never. Courage? Always.
At TikTok, we create together and grow together. That's how we drive impact - for ourselves, our company, and the communities we serve.
Join us.

About The Team:
The mission of the TikTok Eng-AI Innovation Center is to explore cutting-edge AGI technologies, including but not limited to LLM, multi-modal LLM (video/image/audio/text/code), etc., to let machine better understand user creations on Tiktok platform. Regarding to video/image/audio/text, enhanced content understanding can bring better user experience of searching, recommendation, and can more accurately identify and defend internet abuse and fraud on our platform. Regarding to code, our developed LLM aims to automatically re-organize/optimize Tiktok codebase, and make the code/coding become more accessible for Tiktok engineers.

As a project intern, you will have the opportunity to engage in impactful short-term projects that provide you with a glimpse of professional real-world experience. You will gain practical skills through on-the-job learning in a fast-paced work environment and develop a deeper understanding of your career interests.

Applications will be reviewed on a rolling basis - we encourage you to apply early.

Successful candidates must be able to commit to at least 3 months long internship period.

Successful candidates must be able to commit to either of the following Internships
- From January to June
- From May to August (Summer)

Responsibilities:
For Code Optimization:
1. Research and Develop Code Optimization Techniques: Conduct in-depth research into new methodologies for LLM-based code optimization, focusing on automating and enhancing source code according to human-provided specifications. This involves staying abreast of the latest advancements in AI and identifying opportunities to implement these breakthroughs in practical applications.

2. Implement Advanced Inference Techniques: Utilize state-of-the-art inference scaling laws (such as MCTS, A* search, beam search, etc.) to improve the efficiency, accuracy, and capability of LLMs to handle complex coding tasks. This responsibility is crucial for ensuring that the models can generate high-quality code that meets the diverse needs of developers.

3. Enhance Model Reasoning and Inference: Focus on enriching the model's capacity for reasoning and inference by training on diverse and extensive coding datasets, ensuring the generation of sophisticated and reliable code. Developing the model's reasoning abilities is key to achieving sophisticated code generation that addresses complex programming challenges effectively.

4. Publish research papers top-tier AI conference.

For AI-Driven Content Moderation:
1. Develop and Implement AI Moderation Systems: Design and build AI-driven content moderation systems that enhance content understanding and situational awareness, ensuring adherence to community guidelines to maintain safe and compliant online spaces. This responsibility is vital for creating robust and scalable tools that can manage vast amounts of user-generated content effectively.

2. Leverage Advanced Multimodal Techniques: Utilize advanced multimodal techniques to automatically interpret and perceive the nuances of user-generated content. This capability is crucial for accurately identifying and processing content that may pose risks or violate community standards.

3. Embed Dynamic Decision-Making Processes: Integrate dynamic, rule-based decision-making processes informed by community standards and legal requirements to prioritize risk management and ensure immediate responses to high-risk content. This ensures that the content moderation system can act swiftly and appropriately to maintain a safe online environment.

4. Publish research papers top-tier AI conference.