Responsibilities

• Design, build, and optimize scalable backend services supporting both traditional search and AI-powered search systems.
• Own the architecture of search-related systems to ensure high reliability, performance, and scalability.
• Develop reusable backend frameworks and infrastructure to accelerate search and AI product development.
• Collaborate closely with data scientists and AI engineers to enable LLM-powered search, ranking, and agent capabilities.
• Continuously improve search performance, including indexing, retrieval, ranking, and latency optimization.
• Translate business needs into scalable search solutions.
• Drive execution and deliver results in complex or evolving environments.

Requirements

• 5+ years of backend engineering experience.
• Strong proficiency in Java and Python.
• Experience designing and building large-scale distributed systems.
• Hands-on experience with search technologies (e.g., Elasticsearch, vector search, hybrid retrieval) is preferred.
• Experience with big data processing frameworks such as Flink or Spark for real-time or batch data processing.
• Familiarity with AI-powered search technologies, including LLM-based search, RAG architectures, or agent frameworks (e.g., Dify, LangChain, Mastra, OpenAI Agents SDK).
• Familiarity with cloud infrastructure and scalable system design.
• Ability to deliver results in environments with ambiguity or evolving requirements.