ByteDance

6 days ago

Conversational AI Large Model Researcher-Global E-commerce-Soaring Star Talent Program

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI

Last checked: 53 minutes agoStatus: Live

Job Summary

Build an LLM-based customer service chatbot for TikTok and Douyin e-commerce, powering intelligent, end-to-end inquiry handling. Design a multi-agent framework (planning, reply, and tool agents) that negotiates solutions, enforces platform policies, validates tool usage, and adapts dynamically to user behavior. Tackle self-reflection, complex multimodal image understanding, and compliance-focused reasoning to improve service quality at scale.

Location: Singapore

Workplace: Onsite

Employment Type: Full time

Job Function: Research & Scientific (R&D)

Key Responsibilities

•Develop an LLM-based customer service chatbot for TikTok and Douyin e-commerce to handle the full user inquiry process (clarification, negotiation, and execution).
•Design a multi-agent LLM framework with planning-agent, reply-agent, and tool-agent to manage the end-to-end service workflow.
•Ensure reply-agent outputs comply with platform policies and service guidelines while minimizing hallucinations and excessive improvisation.
•Enable planning-agent to identify user demands and problem scenarios while sourcing relevant guidelines/constraints and recognizing risk scenarios.
•Implement tool-agent validation for legal tool usage, correct tool result interpretation, and proper execution dependency management.

Key Requirements

•PhD degree, preferably in computer science, software engineering, artificial intelligence, mathematics, or a related field.
•Strong foundation in machine learning and in-depth understanding of deep learning, multimodal models, and generative models, with strong math and ability to self-learn.
•Proficiency with machine learning frameworks (e.g., PyTorch, TensorFlow) and strong coding skills.
•Experience with multimodal large models, especially long-text processing or film/television drama domains.
•Published papers in top-tier CS conferences/journals (e.g., NeurIPS, ICML, CVPR, ICCV, ECCV, IJCAI, AAAI, KDD, SIGIR, WWW, ACL, PAMI, IJCV) or competition experience.

Education:PhD / Doctorate

Skills:Self-learningMathematical reasoningCodingResearch capability

Tech Stack:LLMMultimodal modelsGenerative modelsPyTorchTensorFlow

Company Brief

ByteDance

Develops consumer internet and content platforms, including TikTok and other apps for short-form video, news, and entertainment. It also builds advertising, commerce, and creator tools that connect audiences, brands, and publishers across global markets.

Industry: Digital Media

Company Size: Enterprise (1,001+ employees)

Revenue: USD 1B+

Growth: Established Company

Headquarters: Beijing, China

Founded: 2012

Website LinkedIn

Loading job details...

Preparing the role view and application actions.

ByteDance

6 days ago

Conversational AI Large Model Researcher-Global E-commerce-Soaring Star Talent Program

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI

Last checked: 53 minutes agoStatus: Live

Job Summary

Location: Singapore

Workplace: Onsite

Employment Type: Full time

Job Function: Research & Scientific (R&D)

Key Responsibilities

•Develop an LLM-based customer service chatbot for TikTok and Douyin e-commerce to handle the full user inquiry process (clarification, negotiation, and execution).
•Design a multi-agent LLM framework with planning-agent, reply-agent, and tool-agent to manage the end-to-end service workflow.
•Ensure reply-agent outputs comply with platform policies and service guidelines while minimizing hallucinations and excessive improvisation.
•Enable planning-agent to identify user demands and problem scenarios while sourcing relevant guidelines/constraints and recognizing risk scenarios.
•Implement tool-agent validation for legal tool usage, correct tool result interpretation, and proper execution dependency management.

Key Requirements

•PhD degree, preferably in computer science, software engineering, artificial intelligence, mathematics, or a related field.
•Strong foundation in machine learning and in-depth understanding of deep learning, multimodal models, and generative models, with strong math and ability to self-learn.
•Proficiency with machine learning frameworks (e.g., PyTorch, TensorFlow) and strong coding skills.
•Experience with multimodal large models, especially long-text processing or film/television drama domains.
•Published papers in top-tier CS conferences/journals (e.g., NeurIPS, ICML, CVPR, ICCV, ECCV, IJCAI, AAAI, KDD, SIGIR, WWW, ACL, PAMI, IJCV) or competition experience.

Education:PhD / Doctorate

Skills:Self-learningMathematical reasoningCodingResearch capability

Tech Stack:LLMMultimodal modelsGenerative modelsPyTorchTensorFlow

Company Brief

ByteDance

Industry: Digital Media

Company Size: Enterprise (1,001+ employees)

Revenue: USD 1B+

Growth: Established Company

Headquarters: Beijing, China

Founded: 2012

Website LinkedIn