Backend Software Engineer, Conversational AI - USDS - TikTok : Job Details

Backend Software Engineer, Conversational AI - USDS

TikTok

Job Location : Seattle,WA, USA

Posted on : 2025-06-11T20:31:06Z

Job Description :
Backend Software Engineer, Conversational AI - USDS

Responsibilities

About the TeamThe future of e-commerce customer service is intelligent, efficient, and AI-driven. Our team aims to replace traditional human-agent customer service with an advanced AI-powered conversational system that offers instant, intelligent, and seamless support for TikTok's global e-commerce platform. Using Large Language Models (LLMs) and NLP, we develop an AI customer service system capable of understanding user queries, resolving disputes, guiding transactions, and enhancing the shopping experience without human intervention.

Our AI handles complex customer interactions, including answering product inquiries, resolving order issues, processing refunds, and assisting sellers with operational tasks. We ensure continuous learning and improvement of our AI through LLM post-training, providing more accurate, context-aware, and human-like interactions.

Joining us means being at the forefront of transforming e-commerce customer service, building AI systems that understand, adapt, and deliver intelligent solutions—reducing costs and increasing efficiency for merchants and the platform.

Our organization follows a hybrid work schedule requiring employees to work in the office 3 days a week or as directed by their manager. This model is regularly reviewed and may change.

What You Will Do

  • Develop AI-Powered Customer Service Systems: Design and implement conversational AI agents for handling inquiries, complaints, refunds, disputes, and logistical issues, replacing traditional customer service roles.
  • LLM Post-Training and Efficient Learning: Collaborate with algorithm teams to apply techniques like instruction tuning, reinforcement learning from human feedback (RLHF), and continual learning to optimize AI responses with minimal labeled data.
  • Model Optimization and Deployment: Research model compression, quantization, and inference optimization. Design deployment strategies, improve open-source frameworks, and explore cutting-edge generative AI technologies.
  • RAG Technology and Applications: Lead design and optimization of RAG frameworks, enhance retrieval system performance, implement advanced algorithms, ensure system reliability, and develop evaluation systems to improve business outcomes.
  • Qualifications

    Minimum Qualifications

    • Bachelor's degree or higher in Computer Science, AI, Mathematics, or related fields.
    • Proficiency in Python, Go, C++, or Java.
    • At least 1 year of experience in large-scale software development, especially in high-concurrency and high-availability systems.

    Preferred Qualifications

    • Experience in dialogue agents, LLMs, prompt engineering, or similar areas.
    • Familiarity with open-source projects like Dify, vLLM, sglang.
    • Participation in open-source communities or relevant contributions.
    • Published papers or patents in related fields.

    Candidates must be legally authorized to work in the U.S. This role does not support visa sponsorship.

    #J-18808-Ljbffr
    Apply Now!

    Similar Jobs ( 0)