Machine Learning Engineer Graduate (Ads Targeting)- 2027 Start
TikTok
- Location
- San Jose, California, United States of America
- Employment
- Full Time
- Work model
- On-Site
- Level
- New Grad
- H-1B history
- 148 approvals (FY2023)
About this role
TikTok Ads Core ML Team aims at creating automatic delivery products for the next generation and developing advertising as a global business, instead of just a monetization tool to consolidate the delivery funnel framework allowing multiple teams to iterate parallel. All of our team effort, is to continuously pursue and establish a world-leading ranking model & framework that always benefits our collaborators, users and customers to get better returns.
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: - Contribute to core ads targeting algorithms, including: - User Modeling: user interest/intent representation, embeddings, sequential behavior modeling, feature engineering - Lookalike Modeling: seed audience expansion, similarity learning, retrieval & ranking strategies, cold-start handling - Auto Targeting: automatic targeting selection/expansion, explore–exploit strategies, multi-objective optimization (performance/cost/reach) - Support offline training and evaluation pipelines: sampling, feature building, training, metrics and visualization - Assist with online A/B testing and analysis; track key KPIs (CTR/CVR/CPA/ROAS) and troubleshoot issues - Collaborate with product/data/engineering to productionize models in the ads delivery stack (retrieval, prediction, bidding/budget constraints, delivery strategies)