ML Engineer: Scalable Recommendations & Personalization

TikTok USDS Joint Venture; San Jose (CA); On-site; USD 123,000 - 259,000; Full time

Job summary

TikTok USDS Joint Venture LLC is seeking applied ML engineers and data scientists to advance general and e-commerce feed recommendations. You will work on large-scale systems, build user-interest models, and develop predictive ranking models with real-time data pipelines.

The team emphasizes applying deep learning with scalable data processing, collaborating across disciplines, and delivering business impact while adapting to an in-person work schedule up to five days per week.

Qualifications

• Bachelor's degree or higher in Computer Science or related fields.
• Strong programming and problem-solving ability.
• Experience with ML algorithms such as Collaborative Filtering, Matrix Factorization, Factorization Machines, Word2vec, Logistic Regression, Gradient Boosting Trees, Deep Neural Networks, Wide and Deep etc.
• Experience with Deep Learning Tools such as TensorFlow/PyTorch.
• Experience with at least one programming language like C++/Python or equivalent.

Responsibilities

• Participate in building large-scale recommendation algorithms and systems (10M–100M users) in TikTok.
• Build long and short term user interest models and extract insights from large data.
• Design, develop, evaluate and iterate on predictive models for candidate generation and ranking, including real-time data pipelines and feature engineering.
• Design and build supporting/debugging tools as needed.

Skills

Programming

Machine learning

Deep learning

C++/Python

Problem solving

Education

Bachelor's degree or higher in CS

Tools

TensorFlow

PyTorch

Job description

TikTok USDS Joint Venture LLC is seeking applied ML engineers and data scientists to advance general and e-commerce feed recommendations. You will work on large-scale systems, build user-interest models, and develop predictive ranking models with real-time data pipelines.

The team emphasizes applying deep learning with scalable data processing, collaborating across disciplines, and delivering business impact while adapting to an in-person work schedule up to five days per week.