The Signal & Measurement team at TikTok Ads owns the full stack of advertising effectiveness — from signal collection and identity resolution to attribution modeling and causal measurement. We build the systems and models that help advertisers worldwide understand and maximize the true business value of their ad spend on TikTok.
Our work sits at the intersection of large-scale machine learning and causal inference, applied at massive scale to answer the hardest question in advertising: "Did this ad actually work?" The team's scope covers four pillars: signal, attribution, identity, and measurement. These outputs directly power downstream ads ranking and delivery models, closing the loop from measurement back to optimization. As a new grad on the team, you will be paired with an experienced mentor, own real projects from day one, and grow across both machine learning and large-scale systems.
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:
- Build and improve machine learning models for signal quality — anomaly detection, signal recovery, denoising, and correction — to ensure the reliability of advertiser conversion data at scale.
- Contribute to cross-platform identity resolution: improve the precision and coverage of our Identity Graph through probabilistic matching models and graph algorithms.
- Participate in attribution model design and implementation, including multi-touch attribution (MTA), modeled conversions, and incrementality measurement.
- Drive the downstream application of signal, identity, and attribution data in ranking models — improve conversion prediction and bidding/ranking quality by feeding higher-fidelity signals, resolved identities, and modeled conversions into ads ranking systems, and own the data-to-model feedback loop end to end.
- Help build large-scale experimentation infrastructure and data pipelines powering Conversion Lift, Brand Lift, Split Test, and cross-media measurement products.
- Explore LLM-powered signal intelligence — apply large language models to the semantic understanding of advertiser conversion data, enabling intelligent classification, quality assessment, and automated correction of event signals.
- Collaborate with Product, Data Science, and Infrastructure teams to turn algorithmic ideas into production systems serving advertisers globally.
Minimum Qualifications:
- Individuals who are completing or have recently completed a Bachelor's or above degree in Computer Science, Statistics, Mathematics, Electrical Engineering, or a related technical discipline.
- Solid foundation in machine learning and statistics: comfortable with concepts such as hypothesis testing, regression, probabilistic models, and ideally causal inference.
- Strong programming skills in at least one of Python, Go, Java, or C/C++, with a solid grasp of data structures and algorithms.
- Hands-on ML experience through coursework, research, internships, or personal projects (e.g., training and evaluating models on real-world data).
- Strong communication skills and eagerness to learn in a fast-paced environment.
Preferred Qualifications:
- Internship, research, or project experience in one or more of: computational advertising, recommendation/search ranking, causal inference or A/B experimentation, entity resolution/graph learning, anomaly detection, or applied LLMs/NLP.
- Publications at ML/data mining venues (e.g., NeurIPS, ICML, KDD, WWW) or strong performance in algorithm/ML competitions (e.g., ACM-ICPC, Kaggle).
- Experience with large-scale data processing frameworks (e.g., Spark, Flink) or ML frameworks (e.g., PyTorch, TensorFlow).
- Genuine curiosity about ads tech and how advertisers think about ROI and measurement.