ML Engineer Intern - Generative Recommender Systems

TikTok; Seattle (WA); On-site; USD 50,000 - 68,000; Full time

Benefits offered by this job

Health insurance

Life insurance

Wellbeing benefits

Holidays

Job summary

TikTok in Seattle invites undergraduate interns to join our E-commerce Recommendation Team. You will contribute to building and scaling our recommendation system to enhance shopping experiences for users, with hands-on duties on generative retrieval, LLMs, and retrieval/ranking research.

You'll gain exposure to GPU-based training, RL-based optimization, and real-world data challenges while collaborating with mentors.

Qualifications

• Currently pursuing an Undergraduate in Software Development, Computer Science, Computer Engineering or a related discipline.
• Solid foundation in machine learning and deep learning, with research or project experience in at least one of the following areas: large language models, reinforcement learning, generative models, recommender systems or information retrieval.
• Proficient in Python and at least one mainstream deep learning framework (e.g., PyTorch, TensorFlow, JAX).

Responsibilities

• Generative Recommendation Research: Drive the evolution of recommender systems from discriminative to generative paradigms; explore frontier directions such as generative retrieval and generative re-ranking/blending; continuously improve personalization capabilities while deeply optimizing the training and inference efficiency of generative models on GPUs.
• LLM for Recommendation Research: Leverage Large Language Models (LLMs), Reinforcement Learning (RL), and related techniques to enhance the semantic understanding and reasoning capabilities of recommender systems, addressing core business challenges in e-commerce scenarios (e.g., cold start, long-tail item distribution, and user intent understanding).
• Agentic Recommendation Research: Explore the construction of self-evolving agents and leverage agents to continuously optimize recommender systems; drive the evolution of recommender systems toward agentic architectures capable of keenly perceiving user context and making real-time, personalized decisions and adjustments.
• Long-Term Value and User Experience Modeling: Explore replacing traditional heuristic rule-based systems with LLM and agent capabilities; build next-generation algorithms for measuring and optimizing long-term value (LTV) and user experience, enabling sustainable growth of the platform ecosystem.

Skills

Python

Machine Learning

Deep Learning

PyTorch

TensorFlow

RL/LLM concepts

Education

Undergraduate in Software Development/CS/CE or related

Tools

PyTorch

TensorFlow

JAX

Job description

TikTok in Seattle invites undergraduate interns to join our E-commerce Recommendation Team. You will contribute to building and scaling our recommendation system to enhance shopping experiences for users, with hands-on duties on generative retrieval, LLMs, and retrieval/ranking research.

You'll gain exposure to GPU-based training, RL-based optimization, and real-world data challenges while collaborating with mentors.