About the Team
Our Recommendation Architecture Team is responsible for building up and optimizing the architecture of the recommendation system for TikTok's vertical businesses, providing the most stable and best experience for TikTok users.
We focus on optimizing the recommendation system architecture, ensuring stability and high availability, and improving the performance of both online services and offline data flows.
We work closely with algorithm teams to improve recommendation effectiveness while boosting performance and reducing costs.
We are looking for talented individuals to join our team.
As a graduate, you will get opportunities to pursue bold ideas, tackle complex challenges, and unlock limitless growth.
Successful candidates must be able to commit to an onboarding date by the end of the year. Please state your availability and graduation date clearly in your resume.
Candidates can apply to a maximum of two positions and will be considered for jobs in the order you apply.
The application limit is applicable to our Company and its affiliates' jobs globally.
Applications will be reviewed on a rolling basis - we encourage you to apply early.
Responsibilities
- Participate in the design of the recommendation system to enhance development efficiency, performance, scalability, and recommendation effectiveness.
- Build and maintain high-performance, high-availability online services (retrieval, ranking orchestration, feature and index services) for the TikTok recommendation system.
- Build efficient and reliable data pipelines for candidate generation, profile generation, and training-example generation.
- Pursue extreme performance optimization in the storage layer, computing layer, or application layer; optimize latency (P99), throughput, and resource cost at scale.
- Troubleshoot production issues and build mechanisms that ensure operational stability, including capacity planning, disaster recovery, and monitoring.
- Collaborate with machine learning engineers to productionize models efficiently and safely.