Description
Responsibilities
About the Team Governance and Experience is a global team aiming to build a safe and trustworthy marketplace for not only users, but also partners. We value user experience and work on policies, rules, products and systems to ensure quality. We are looking for passionate talents to join us, thus together we can build a commerce ecosystem that is innovative, secure and intuitive for our users.
As part of GNE organization is our Service Support Centre (SSC) delivers Customer Service to our Buyers, Partners and internal users. We are an AI
- First large language model strategy operation team, responsible for driving the large-scale deployment of LLMs across the e-commerce service ecosystem.
Our mission goes beyond enabling model adoption in isolated service scenarios — we aim to build a sustainable and continuously evolving LLM operating system that transforms model capability into a foundational productivity engine for service efficiency and experience enhancement. Covering the full lifecycle from application development to business value realization, we systematically build the service-side infrastructure, evaluation frameworks, data assets, and standardized operating processes. We play a central role in capability building, solution & process design, and scalable solution implementation.
Through continuous process optimization and data accumulation, we drive LLM adoption from isolated experiments toward structured, measurable, and sustainably value-generating practices. Responsibilities Depending on background and expertise, candidates will focus on one or more of the following core modules: 1. Develop AI solutions based on business requirements
- Translate cutting-edge LLM capabilities into scalable e-commerce service solutions, covering core domains such as aftersales, logistics, and inquiries.
Develop a deep understanding of business know-how, design AI application strategies aligned with real business objectives, validate solutions through experimentation and performance evaluation, and ensure optimization in production environments.
- Standardize implementation methodologies and best practices to enable scalable replication across the organization.
Support cross-functional teams in understanding and applying AI solutions, improving overall adoption maturity and deployment efficiency. 2. Design and build core infrastructure & processes
- Build and govern the LLM infrastructure required for large-scale operations, including model management frameworks, service knowledge maintenance, application evaluation mechanisms, and launch/deprecation governance processes.
Establish unified model/application selection, evaluation, and decision-making standards to reduce the marginal costs of new scenario onboarding and service strategy iteration.
- Lead the development of model/application performance measurement standards, case libraries, and evaluation datasets.
Collaborate closely with algorithm teams to form a closed-loop process for issue identification and optimization, ensuring model performance remains measurable and continuously improving. 3. Provide data annotation and governance solutions
- Establish a unified data asset and annotation governance system to continuously provide high-quality, controlled data for model training, knowledge base maintenance and application evaluation.
Define annotation standards, conduct quality audits, and manage resource allocation to ensure stability, compliance, and reliability of data supply. While maintaining strict quality standards, exploring annotation automation and human-in-the-loop mechanisms to improve data production efficiency and scalability, laying a strong data foundation for ongoing model optimization and capability evolution.
QualificationsMinimum Qualification(s) 1. Systematic Modeling Capability - Strong structured thinking and system-level abstraction ability. Capable of distilling core issues from complex and ambiguous business requirements and translating them into clear strategic frameworks (e.g., PRDs, SOPs, process designs).
Able to further abstract business challenges into standardized workflows, configurable rules, and reusable modules, building scalable operational leverage. 2. LLM & Agent Practical Expertise - Deep understanding of LLM and Agent architectures and working mechanisms. Proficient in prompt engineering, workflow orchestration, tool integration, and advanced context management.
Strong hands-on execution ability, capable of translating model capabilities into deployable business solutions and independently building and validating demos or PoCs. 3. Business–Technology Bridging Capability - Strong cross-functional collaboration skills, able to work effectively with service strategy, algorithm, product, and operations teams. While an algorithmic background is not mandatory, candidates must clearly understand model capability boundaries and practical deployment constraints, serving as a bridge between business and technical teams to co-build scalable system solutions.
Preferred Qualification(s) 1. Experience with rule engines, strategy systems, process automation, or complex decision systems. 2. Experience in e-commerce, customer service, service operations, risk control, or transaction governance within rule-dense and process-complex environments.
3. Experience participating in AI product development from 0 to 1 or scaling from pilot to large-scale deployment.