ByteDance

Responsibilities

About the Team

The Security Engineering team is a research and development (R&D) team that operates within the broader Security Organization. Their core responsibility is to construct, implement, and sustain secure infrastructures, platforms, and technologies. In addition, they provide support to cross-functional teams within ByteDance. The team's ultimate objective is to serve and safeguard ByteDance products and infrastructures on a global scale.

Responsibilities:

• Explore the application of LLM post-training technology in AI For Security;
• Build data labeling, enhancement, and synthesis technologies based on AI to improve training data quality and domain adaptation, and accelerate data iteration;
• Domain specific LLM training, optimization such as instruction fine-tuning and reinforcement learning to improve the ability of large-scale model inference, code, tool use ability etc.
• Radical exploration of high-value technologies and application areas.

Qualifications

Minimum Qualifications:

• Master's or Ph.D. Degree in computer science, or related field;
• Solid knowledge of computer science and machine learning;
• Solid programming skills using go/python/java/c;
• In-depth experience in one or more fields such as risk control, NLP, multi-modal Machine Learning, deep learning, search, recommendation, etc;
• Familiar with large model pre-training, post-training (SFT/RL, etc.), and RAG;
• Good communication and coordination skills, self-motivated.

Preferred Qualifications:

• Published research papers in top conferences/journals in CV/NLP/Security domain;
• Familiar with model acceleration and large-scale training system architecture.