Generative Recommender Systems ML Engineer

TikTok; Seattle (WA); On-site; USD 154,000 - 301,000; Full time

Job summary

TikTok is seeking a PhD-level researcher to join the E-commerce Recommendation Team in Seattle, focusing on advancing recommender systems with generative approaches, LLMs, and agentic architectures. Applicants should be finishing or have recently completed a PhD in a related field and demonstrate strong ML/DL research capabilities.

The role involves exploring cutting-edge techniques for personalized, scalable recommendations and higher‑level user experience optimization, with opportunities for

Qualifications

• PhD or current completion in CS/EE/Math/Stats or related field.
• Strong ML/DL research background with exposure to recommender systems or information retrieval.
• Proficiency in Python and at least one major DL framework (PyTorch, TensorFlow, or JAX).

Responsibilities

• Generative Recommendation Research: evolve recommender systems toward generative paradigms; improve personalization and training/inference efficiency on GPUs.
• LLM for Recommendation Research: utilize LLMs, RL, and related methods to enhance semantic understanding and reasoning in e-commerce recommendations.
• Agentic Recommendation Research: explore self-evolving agents to optimize recommender systems for real-time, personalized decisions.
• Long-Term Value and User Experience Modeling: replace heuristic rules with LLM/agent capabilities to measure and optimize LTV and user experience.

Skills

Python

PyTorch

TensorFlow

JAX

Education

PhD in Computer Science / Electrical Engineering / Mathematics / Statistics or related

Tools

PyTorch

TensorFlow

JAX

Job description

TikTok is seeking a PhD-level researcher to join the E-commerce Recommendation Team in Seattle, focusing on advancing recommender systems with generative approaches, LLMs, and agentic architectures. Applicants should be finishing or have recently completed a PhD in a related field and demonstrate strong ML/DL research capabilities.

The role involves exploring cutting-edge techniques for personalized, scalable recommendations and higher‑level user experience optimization, with opportunities for