Software Engineer, Ads Measurement & Effectiveness

Description

The Signal & Measurement team at TikTok Ads is responsible for 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 distributed systems and causal inference. We operate at massive scale while applying rigorous statistical methodology to answer the hardest question in advertising: "Did this ad actually work?"

What You'll Own
- Design and build signal quality frameworks — anomaly detection, signal recovery, denoising, and correction pipelines that ensure the reliability of advertiser conversion data at scale.
- Develop and optimize cross-platform identity resolution systems, improving the precision and coverage of our Identity Graph through probabilistic matching models and graph algorithms.
- Own attribution model design and implementation end-to-end, including multi-touch attribution (MTA), modeled conversions, and incrementality measurement.
- Build large-scale experimentation infrastructure and real-time data pipelines powering Conversion Lift, Brand Lift, Split Test, and cross-media measurement products.
- Explore LLM-powered signal intelligence — leverage large language models for semantic understanding of advertiser conversion data, enabling intelligent classification, quality assessment, and automated correction of event signals.
- Collaborate cross-functionally with Product, Data Science, and Infrastructure teams to translate algorithmic ideas into production systems serving advertisers globally.

Requirements

Minimum Qualifications：
- BS/MS in Computer Science, Statistics, Mathematics, or a related field.
- Strong software engineering skills; proficient in at least one of: Python, Go, Java, C/C++.
- Solid foundation in data structures, algorithms, and system design.
- Experience building backend or data-intensive systems at scale.
- Foundational knowledge in statistics or machine learning — you should be comfortable with concepts like hypothesis testing, causal inference, regression, and probabilistic models.

Preferred Qualifications：
- Experience in one or more of the following areas:
- Signal processing: conversion data quality, anomaly detection, data imputation and denoising.
- Identity resolution: ID mapping, entity resolution, probabilistic matching, graph algorithms.
- Attribution modeling: last-click, MTA, incrementality, or conversion modeling.
- Experimentation: A/B testing, Lift Studies, or productionizing causal inference methods.
- Adjacent algorithm domains such as recommendation systems, search ranking, or computational advertising.
- Ability to independently drive the full lifecycle — from problem definition and model design to production deployment — rather than solely implementing specs written by others.
- Domain knowledge in ads tech and a genuine curiosity about how advertisers think about ROI and measurement.