AI Engineer - LLM & AI Agent

Job Summary

The role will support initiatives such as secure enterprise RAG platforms, corporate knowledge systems, domain-specific assistants, proactive AI agents, document intelligence, and workflow automation.

The successful candidate should have strong Python and AI application development skills and be able to independently own and deliver end-to-end LLM, RAG, and AI agent projects.

Responsibilities

• Design, develop, and improve LLM-based applications, RAG systems, AI assistants, and agentic AI solutions for product and enterprise use cases.

• Develop proactive and interactive AI agents that can understand user requests, retrieve information, use tools, execute workflows, and interact through text or voice.

• Build and optimize core capabilities such as document ingestion, information retrieval, prompting, tool calling, agent orchestration, memory, and human-in-the-loop control.

• Integrate AI agents with devices, internal systems, databases, APIs, document repositories, and third-party services.

• Evaluate and apply appropriate technologies, including LLMs, speech models, vector databases, retrieval methods, knowledge graphs, and agent frameworks.

• Define and implement evaluation methods for retrieval quality, response accuracy, faithfulness, task completion, latency, reliability, and safety.

• Implement secure and reliable AI application patterns, including access control, permission-aware retrieval, guardrails, monitoring, and failure handling.

• Independently lead assigned AI projects from use-case definition and solution design through development, testing, deployment, and continuous improvement.

• Collaborate with product, software, cloud, embedded, data, IT, security, and business teams to deliver practical AI solutions.

• Monitor application performance, analyze failures and user feedback, and continuously improve system quality and usability.

Required Qualifications

• Bachelor’s degree or above in Computer Science, AI, Machine Learning, NLP, Data Science, Engineering, or a related field.

• At least 2 years of relevant experience in LLM applications, information retrieval, RAG, AI agents, NLP, or AI application development.

• Strong Python programming skills and experience developing maintainable applications or backend services.

• Hands-on experience with LLM APIs, open-source LLMs, embeddings, vector databases, semantic search, or retrieval systems.

• Practical understanding of RAG architecture, prompt engineering, retrieval strategies, evaluation, and hallucination mitigation.

• Experience with tool calling, function calling, agent workflows, APIs, databases, or backend integration.

• Ability to independently design and deliver end-to-end LLM, RAG, AI agent, or AI application projects.

• Familiarity with Git, automated testing, documentation, CI/CD, and containerized deployment.

• Good communication skills and ability to work with technical and non-technical stakeholders.

Preferred Qualifications

• Experience with LangChain, LangGraph, LlamaIndex, Haystack, Semantic Kernel, or similar frameworks.

• Experience with Qdrant, Milvus, Elasticsearch, OpenSearch, pgvector, Neo4j, or similar technologies.

• Experience with hybrid search, reranking, knowledge graphs, document intelligence, or GraphRAG.

• Experience with agent frameworks, MCP-compatible integration, workflow orchestration, or multi-agent systems.

• Understanding of secure RAG, access control, data privacy, and enterprise AI governance.

• Experience deploying LLM applications in cloud, private, on-premises, or hybrid environments.

• Familiarity with Docker, Kubernetes, observability, tracing, and evaluation tools.

• Professional proficiency in English; Mandarin or Cantonese is an advantage.