Building a world where people can safely discover, create and connect. The Trust & Safety (T&S) team at TikTok helps ensure that our global online community is safe and empowered to create and enjoy content across all of our applications. We have invested heavily in human and machine-based moderation to remove harmful content quickly and often before it reaches our general community.
About the Team
The Search Operations team aims to improve search user experience, contribute significant DAU impact to the products and drive for increase in traffic and GMV.
The T&S evaluation and investigation team, working closely with the search team, taking the evaluation standards as the baseline and principles, and manually evaluating the search query and the corresponding search results page to reflect the real user experience of the search function.
The team is committed to providing search and evaluation services for international products, with resource support provided by different countries around the world, and global members conduct evaluations according to unified guidelines. The evaluation scope covers multiple search sections, such as basic search experience, recommended search, search advertising, and search security. As a bridge for business communication domestically and abroad, the team is responsible for key nodes such as standard writing, training Q&A, report output, and human efficiency management to effectively promote the execution and implementation of projects.
It is possible that this role will be exposed to harmful content as part of the core role/as part of project/ in response to escalation requests/by chance.
This may occur in the form of images, video, and text related to every-day life, but it can also include (but is not limited to) bullying; hate speech; child safety; depictions of harm to self and others, and harm to animals.
What will I be doing?
- Complete regular assessments related to AI model quality based on business requirements in accordance with evaluation standard documents. Major in journalism, literature, mathematics, computer science, medicine, law, economics are preferred
- Use evaluation methods to complete daily strategy assessment of AI model quality and comb the types of bad cases to rate the quality of the results
- Provide ideal AI model search results and elaborate logical reasons to support the evaluation given
- Note: The output evaluation results will serve as an important basis for search strategy optimization and product function planning.
- Work closely with the QA to provide feedback on data quality, SOP and guidelines to support overall project success
- Perform other ad-hoc duties in relevant projects as assigned
Report job
