Responsibilities

About ByteDance
Founded in 2012, ByteDance's mission is to inspire creativity and enrich life. With a suite of more than a dozen products, including TikTok, Helo, and Resso, as well as platforms specific to the China market, including Toutiao, Douyin, and Xigua, ByteDance has made it easier and more fun for people to connect with, consume, and create content.

Why Join Us
Creation is the core of ByteDance's purpose. Our products are built to help imaginations thrive. This is doubly true of the teams that make our innovations possible. Together, we inspire creativity and enrich life - a mission we aim towards achieving every day. To us, every challenge, no matter how ambiguous, is an opportunity; to learn, to innovate, and to grow as one team. Status quo? Never. Courage? Always. At ByteDance, we create together and grow together. That's how we drive impact - for ourselves, our company, and the users we serve. Join us.

About the team
Responsible for requirement analysis and strategy optimization of Big Language Model, responsible for data quality and model effect, and working with multiple teams such as evaluation and R & D to improve model effect

Responsibilities:
1. Draft, revise, and manage non-safety labeling guidelines to satisfy both LLM model alignment requirements and the feasibility of human operations.
2. Conduct quality assurance and participate in daily calibration meetings with technical and product teams to understand current policy execution challenges and identify any gaps.
3. Collaborate with data analysts and operations managers to evaluate the effectiveness of current guidelines, assess the impact of guideline changes, and recommend major initiatives for updating the policy framework and content.
4. Engage with and interview external stakeholders to learn the best practices and domain expertise for guideline development and iteration.

Qualifications

Job requirements
1. A solid understanding of alignment methodologies, including but not limited to Supervised Fine-Tuning (SFT), Reinforcement Learning from Human Feedback (RLHF), etc., is essential. Alternatively, substantial experience in developing moderation policies from the ground up is acceptable.
2. A minimum of three years' experience in guideline development is required. The candidate should be adept at analyzing cases and structuring actionable and impactful guideline revisions.
3. Proficiency in English is a prerequisite for this role.
4. A keen interest in Large Language Models (LLMs) and human behavior, experience, and wellbeing is crucial. The ideal candidate will be an avid learner and should find in-depth case studies and engagement with labelers from diverse backgrounds stimulating rather than monotonous or laborious.

ByteDance is committed to creating an inclusive space where employees are valued for their skills, experiences, and unique perspectives. Our platform connects people from across the globe and so does our workplace. At ByteDance, our mission is to inspire creativity and enrich life. To achieve that goal, we are committed to celebrating our diverse voices and to creating an environment that reflects the many communities we reach. We are passionate about this and hope you are too.