Responsibilities
1. Responsible for the quality closed loop of the entire process of Douyin intelligent creation-camera product development, including but not limited to: participating in product plan review, test plan design, test execution, and online and offline quality analysis, etc. 2. Discover pain points and inefficiencies in work, and be able to combine AI technology to systematically improve efficiency and quality, and apply large model capabilities to all aspects of quality assurance, including but not limited to: LLM-based test case generation, multi-modal model-based effect evaluation and anomaly detection, Agent-based automated testing and problem attribution analysis, and participate in the entire process from mining scenarios solution design technology implementation revenue measurement 3. Responsible for establishing quality measurement standards, monitoring, locating and troubleshooting project issues to drive product quality improvement 4. Pay attention to industry technologies (LLM, multi-modal models, AIGC, etc.), learn and research new technologies, and continuously enrich the testing capabilities within the team 5. Establish an efficient collaboration process with product and R&D teams, and make suggestions for product improvement, explore new quality assurance paradigms based on AICoding, and improve user product experience.
Qualifications
1. Bachelor degree or above, computer-related majors are preferred 2. Have certain software testing experience, familiar with testing theories and methods, and have good communication, collaboration and problem analysis skills 3. Master one or more languages, such as Python/Node.js/Java/Objective-C, and be familiar with commonly used testing tools and testing frameworks on the server and client 4. Understand Android/iOS/Hongmeng system features and language features, relevant special testing experience is preferred 5. Have technical practical experience related to AI large models, and practical implementation experience in one or more of the following directions is preferred: LLM applications (Prompt Engineering, RAG, Agent, etc.), multi-modal models (image/video understanding, generation models), model fine-tuning (SFT/LoRA/DPO, etc.), AI applications in the testing field (such as automatic generation of use cases, intelligent evaluation, defect analysis, etc.).
