ML Engineer: Foundation Models for Smart E‑commerce Recs

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

Benefits offered by this job

Medical, dental, vision insurance

401(k) with company match

Parental leave

Disability insurance

Life insurance

Wellbeing benefits

Paid holidays

Paid sick days

Paid personal time

Job summary

TikTok USDS Joint Venture LLC is seeking researchers and engineers to advance a unified, event-sequence-driven foundation model for cross-business recommendation systems. The role emphasizes integrating multimodal signals and LLMs to improve retrieval, ranking, and re-ranking across multiple scenarios.

You will contribute to end-to-end generative recommendation research, system optimization, and experiments in an open, collaborative environment where ideas are tested and validated with code and

Qualifications

• Proficient in Python with exposure to mainstream ML frameworks.
• Experience with ML or information retrieval research is required.
• Strong passion for intelligent recommendation systems and a self-driven research mindset.
• Comfortable working in a fast-paced research-engineering environment.

Responsibilities

• Build and optimize cross-scenario Foundation Models for unified modeling and efficient inference.
• Apply LLM technologies across retrieval, ranking, and re-ranking stages and contribute to model training and inference optimization.
• Explore integrating LLMs/VLMs with recommendations to create adaptive intelligent systems.
• Research end-to-end generative recommendation and system optimization methods balancing efficiency and UX.

Skills

Python

PyTorch

Machine Learning

Information Retrieval

Education

Bachelor's or Master's in CS/ML

Job description

TikTok USDS Joint Venture LLC is seeking researchers and engineers to advance a unified, event-sequence-driven foundation model for cross-business recommendation systems. The role emphasizes integrating multimodal signals and LLMs to improve retrieval, ranking, and re-ranking across multiple scenarios.

You will contribute to end-to-end generative recommendation research, system optimization, and experiments in an open, collaborative environment where ideas are tested and validated with code and