Design and implement workload scheduling across multiple data centers, regions, and cloud environments, ensuring balanced resource utilization and efficient placement of both online services and offline batch jobs.
Enhance observability for recommendation systems in complex global environments, including multi-region, multi-data center, and multi-language scenarios; establish end-to-end tracing systems and optimize issue attribution mechanisms.
Assess the security of AI-powered features and internal AI tooling — prompt injection, unsafe tool/agent invocation, data leakage and over-permissive integrations.
Analyse user needs and develop software solutions for distributed system, applying principles and techniques of computer science, engineering, and mathematical analysis;
Vertical Search Team: Build a full-stack search engine serving billions of global users, covering vertical scenarios such as photo-text search, user search, live search and music search. The scope also encompasses AI-powered search for standalone apps including Drama and Lemon8. We leverage LLM, NLP, and multimodal understanding technologies to iteratively enhance search quality and system performance.
Innovate & Apply: Stay ahead of industry trends in search engine technology and distributed systems, Work on Retrieval-Augmented Generation (RAG) applications and provide highly relevant, context-aware search results. Design and develop the backend infrastructure for Agentic Search, enabling complex reasoning and multi-step query processing at scale.