Responsibilities
TikTok Core Feed Recommendation team sits in the center of TikTok, designs, implements and improves the core recommendation algorithm that powers the "for you" feed, "following" feed, etc. of the TikTok app. The recommendation system we built connects hundreds of millions of users with relevant content out of billions of videos in real-time, and inspires high-quality content creation for millions of creators on the platform.
The User Growth team is an essential pillar of the Core Feed Recommendation team, directly responsible for implementing and refining new user acquisition and retention strategies. Our team is committed to achieving TikTok's ultimate goals through developing high-performance models and sound strategies. We take pride in our rigorous approach to applied research, innovative system design, and steadfast pragmatism.
Want more jobs like this?
Get Data and Analytics jobs in Singapore delivered to your inbox every week.
We are looking for strong research scientists and engineers at all levels, who are excited about growing their business understanding, building highly scalable and reliable software, and partnering across disciplines with global teams, in pursuit of excellence.
What you'll do:
- Implement machine learning algorithms at large scales to optimize and improve new user acquisition efficiency, and leverage acquisition signals to improve new user retention across all ranking phases including but not limited to retrieval, ranking, re-ranking and etc.
- Work cross functionally with product managers, data scientists and product engineers to understand insights, formulate problems, design and refine machine learning algorithms, and communicate results to peers and leaders.
- Run regular A/B tests, perform analysis and iterate algorithms accordingly.
- Have a good understanding of end-to-end machine learning systems. Work with infra teams on improving efficiency and stability.
Qualifications
Minimum Qualifications
• Hands-on experience in one or more of the areas: recommender systems, machine learning, deep learning, pattern recognition, data mining, computer vision, NLP, causal inference, content understanding or multimodal machine learning
• Strong programming skills in Python and/or C/C++, and a deep understanding of data structures and algorithms
• Familiar with architecture and implementation of at least one mainstream machine learning programming framework (TensorFlow/Pytorch/MXNet)
• Good communication and teamwork skills, be passionate about learning new techniques and taking on challenging problems
• Prior industry experience with main components of recommendation systems(retrieval, ranking, re-ranking, cold-start etc.) is a plus but not required
Preferred Qualifications
1. Publications at main conferences such as KDD, NeurIPS, WWW, SIGIR, WSDM, CIKM, ICLR, ICML, IJCAI, AAAI, RecSys or related conferences
2. Strong tracking record of success in data mining, machine learning, or ACM-ICPC/NOI/IOI competitions
3. Participation in public/open-source AI-related projects which are of high visibility