Responsibilities
- Lead by example in the design and development of high-availability, enterprise-level AI-based applications
- Architect solutions and mentor other engineers
- Design and develop AI-based applications using latest AI technologies and software practices
Requirements
- Proven hands-on experience building and integrating AI / LLM applications in production, using models such as DeepSeek, Qwen, ChatGPT, and other open-source or commercial large language models
- Solid experience designing and implementing Retrieval-Augmented Generation (RAG) systems, including knowledge base construction, document ingestion pipelines, chunking/embedding strategies, and retrieval orchestration
- Practical experience working with vector databases such as Milvus, OceanBase, FastGPT, Weaviate, Qdrant, or similar technologies to power semantic search and RAG-based applications
- Hands-on experience designing and implementing AI agents / agentic workflows, ideally using frameworks such as LangGraph (or similar), and developing Model Context Protocol (MCP) servers/clients, including tool-calling, multi-step reasoning, and orchestration across external systems
- Strong technical proficiency in python, Typescript, React.js, and Node.js, with significant experience in cloud deployment environments, especially AWS
- Experience with Docker, Kubernetes, and CI/CD pipelines, demonstrating a solid understanding of DevOps practices
- A deep understanding of Agile methodologies, with the ability to mentor others in Agile practices
