Senior ML Engineer — Generative Recs & Foundation Models

TikTok USDS Joint Venture; Seattle (WA); On-site; USD 130,000 - 246,000; Full time

Job summary

TikTok USDS Joint Venture in Seattle is seeking researchers to build a unified Foundation Model for multi-business recommendation systems, spanning retrieval to re-ranking, with emphasis on event-sequence generative paradigms and multimodal integration.

We value open exploration and empower engineers to propose hypotheses and validate ideas in an open environment, enabling fast iteration and impactful work on end-to-end intelligent recommenders within a collaborative, on-site team.

Qualifications

• Bachelor's or Master's degree in CS, ML, or a related field.
• 1+ years of experience in ML, DL, or information retrieval.
• Proficiency in Python and PyTorch.
• Strong passion for intelligent recommendation systems and a self-driven research mindset.

Responsibilities

• Build and optimize cross-scenario shared Foundation Models to enable unified modeling and efficient inference.
• Apply LLM technologies across retrieval, ranking, and re-ranking stages; participate in model training, inference optimization, and system co-design.
• Explore the integration of LLMs / VLMs with recommendation systems to develop adaptive and evolving intelligent recommenders.
• Research end-to-end generative recommendation and system optimization methods that balance efficiency and user experience.

Skills

Python

Deep learning

Information retrieval

Research mindset

Education

Bachelor's or Master's in CS/ML or related field

PhD in CS/ML or related field

Tools

PyTorch

Job description

TikTok USDS Joint Venture in Seattle is seeking researchers to build a unified Foundation Model for multi-business recommendation systems, spanning retrieval to re-ranking, with emphasis on event-sequence generative paradigms and multimodal integration.

We value open exploration and empower engineers to propose hypotheses and validate ideas in an open environment, enabling fast iteration and impactful work on end-to-end intelligent recommenders within a collaborative, on-site team.