Machine Learning Engineer Graduate (Ads Targeting)

About the Role

TikTok Ads Core ML Team is developing next-generation automatic delivery products to establish advertising as a global business. The team focuses on a consolidated delivery funnel framework to enable parallel iteration across multiple teams and to build a world-leading ranking model & framework that benefits collaborators, users, and customers. We are looking for talented individuals to join our team as Graduate Machine Learning Engineers. Successful candidates must be able to commit to an onboarding date by the end of the year.

Key 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)

Requirements & Tech Stack

• Strong coding skills in Python; C++/Go is a plus
• Solid ML/DL/LLM fundamentals (LR/GBDT, DNNs, LLM, evaluation, regularization, tuning)
• Comfortable with data tools (SQL, Pandas); Spark/Flink/Hive is a plus
• Passionate about ads/recommenders/growth and learning business metrics

Qualifications

• Individuals who are completing or have recently completed a Bachelor's/Master's degree in Computer Science, Mathematics, Statistics or a related discipline.
• Experience in ads targeting, recommender systems, search, retrieval/ranking, representation learning, causal/experimentation is preferred.
• Hands-on with PyTorch/TensorFlow; familiarity with production inference is preferred.
• Large-scale data processing, feature platforms, vector search (ANN) is preferred.
• Availability and graduation date must be clearly stated in the resume.
• Candidates can apply to a maximum of two positions. Applications will be reviewed on a rolling basis.