Back to jobs
TikTok10K+ employees

Machine Learning Engineer, Data Mining (Ads Core)

San Jose, CASalary not listedAdded to Openbound 25 days ago

Job description

Monetization Technology teams are building the next-generation monetization platforms to help millions of customers grow their businesses, utilizing our products like TikTok. Our team develops a wide variety of advertisements for numerous uses including feeds, live streaming, branding, measurement, targeting, search, vertical solutions, creative solutions, and business integrity.

What You'll Do:

  • Own foundational targeting data and platform capabilities with high availability, accuracy, freshness, and scalability:
  • Base targeting dimensions: gender, age, geo, device, language, network, etc.
  • Audience & tagging system: definitions, hierarchy, refresh strategy, backfills, cross-device unification
  • Design and implement large-scale batch/stream pipelines: ingestion, ETL, aggregation, profile generation, tag updates, external serving
  • Build a reliable data quality framework: validation, lineage, monitoring/alerting, SLAs, automated backfill and repair
  • Provide standardized capabilities for ads delivery/strategy systems:
  • Audience package generation/management, tag query services, foundational targeting rule engine, access control & auditing
  • Collaborate with ML/product/compliance to ensure stable production rollout and iterative improvements (performance/reach/cost/UX)

Qualifications

Minimum Qualifications:
- BS+ in CS/SE/Data Engineering or related fields

- 3+ years (adjustable) in data engineering/platform roles; able to own critical pipelines end-to-end

- Strong SQL and data modeling; hands-on with big data stack (Spark/Hive/Kafka/Flink/Airflow, etc.)

- Proficient in Java/Scala/Python; solid engineering and performance tuning skills

- Strong ownership of data governance, definitions, quality and stability

- Effective cross-functional communication and execution

Preferred Qualifications:

  • Experience in ads/recommender data platforms: user profiles, tagging, audience segmentation, DMP/CDP
  • Real-time profile or low-latency serving at scale (high QPS, caching/consistency)
  • Privacy/compliance implementation experience (minimization, anonymization, access control, auditing)