AI Agent Engineer - TikTok LIVE (Singapore)

TikTok
Singapore
Workplace: OnsiteFull timeFunction: Data Science & Machine LearningSkills: ["Problem decomposition","System design","Technical curiosity","Learning agility","Collaboration"]

Build and evolve TikTok LIVE’s Performance Analysis Agent, turning LLM/agent capabilities into an end-to-end engine for performance optimization. Design agent workflows for automatic data inspection and attribution, automated A/B experiment reporting, thematic performance insights, and shift-left code performance review. Develop agent platform services (MCP-based), improve accuracy and efficiency with prompt engineering, CoT, RAG, function calling, and evaluation loops, and close the AI value loop with product/R&D teams.

Loading

Loading job details...

Preparing the role view and application actions.

FursaFursa
TikTok
TikTok
1 month ago

AI Agent Engineer - TikTok LIVE (Singapore)

✓ Verified Job

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

Source: Company careers pageValidated by: Fursa AI
Last checked: 10 minutes agoStatus: Live

Job Summary

Build and evolve TikTok LIVE’s Performance Analysis Agent, turning LLM/agent capabilities into an end-to-end engine for performance optimization. Design agent workflows for automatic data inspection and attribution, automated A/B experiment reporting, thematic performance insights, and shift-left code performance review. Develop agent platform services (MCP-based), improve accuracy and efficiency with prompt engineering, CoT, RAG, function calling, and evaluation loops, and close the AI value loop with product/R&D teams.
Location: Singapore
Workplace: Onsite
Employment Type: Full time
Job Function: Data Science & Machine Learning

Key Responsibilities

  • •Design and develop core capabilities of the Performance Analysis Agent for performance analysis workflows, including data inspection/attribution, automated experimental analysis, thematic insights, and shift-left code performance review.
  • •Build and evolve the agent platform and services by upgrading APIs into an MCP (Model-Controller-Proxy) service framework and strengthening data/tooling for scalability and reliability.
  • •Improve agent core performance by enhancing understanding, retrieval, decision-making, and responses using prompt engineering, CoT, RAG, function calling, and memory/evaluation iteration.
  • •Establish a robust scientific evaluation system for agent learning and iteration.
  • •Drive an AI value closed loop by partnering with business, product, and R&D teams to turn AI solutions into measurable improvements in efficiency, service quality, and user experience metrics.

Key Requirements

  • •Possess strong engineering and implementation skills with solid software engineering fundamentals, including the ability to design and implement complex systems.
  • •Familiarity with large language models (LLMs) and agent paradigms, plus practical experience integrating AI technologies into real-world workflows.
  • •Able to decompose and design scalable system architectures from complex, ambiguous business problems.
  • •Demonstrate strong technical curiosity and a fast learning ability for cutting-edge technologies and best practices.
  • •Preferred: hands-on project experience with AI agents; experience in performance analysis, observability, or data analysis; basic live streaming stack knowledge; open-source involvement.
Experience:AI agentsLLMsLive streamingPerformance analysisObservabilityData analysis
Skills:Problem decompositionSystem designTechnical curiosityLearning agilityCollaboration
Tech Stack:GoPythonJavaRustC++LLMsAgent paradigmsMCPModel-Controller-ProxyPrompt engineeringChain of Thought (CoT)Retrieval-Augmented Generation (RAG)Function callingA/B experimentsCode reviewEvaluation system

Company Brief

TikTok
Short-form video platform that lets users create, share, and discover entertainment content through algorithmic recommendations. It also offers advertising and creator tools for brands, influencers, and businesses.
Industry: Digital Media
Company Size: Enterprise (1,001+ employees)
Growth: Scaleup
Headquarters: Singapore, Singapore
Founded: 2016
WebsiteLinkedIn