Responsibility:

• Lead the design, development, and deployment of enterprise-grade LLM and Agentic AI applications.
• Build intelligent multi-step AI workflows involving planning, tool execution, reasoning, retries, and structured outputs.
• Design scalable and reliable application architectures beyond proof-of-concept solutions.
• Integrate AI solutions with APIs, enterprise platforms, databases, and front-end applications.
• Develop and optimise Retrieval-Augmented Generation (RAG) pipelines, vector search, embeddings, and context management frameworks.
• Establish best practices for LLM evaluation, testing, monitoring, observability, and version management.
• Drive performance optimisation across AI applications, including latency, cost efficiency, reliability, and security.
• Translate business requirements into practical technical solutions and architectural designs.
• Collaborate closely with Data Scientists, Product Teams, Engineers, and business stakeholders to deliver AI initiatives.
• Contribute to engineering excellence through code reviews, technical guidance, and continuous improvement of development standards.

Requirements:

• Bachelor's degree in Computer Science or a related field.
• 5+ years of software engineering experience with strong Python development skills.
• Proven experience delivering production-ready LLM, GenAI, or Agentic AI solutions.
• Hands-on expertise with agent frameworks such as LangGraph, LangChain, or similar technologies.
• Solid knowledge of RAG, vector databases, embeddings, and LLM orchestration.
• Experience in integrating AI applications with APIs, enterprise systems, databases, and front-end platforms.
• Strong with LLMOps, evaluation frameworks, testing, monitoring, and observability.
• Excellent problem-solving, communication, and stakeholder management skills.

If you're interested in this role, please forward your latest resume to cheryl.NG@hays.com.hk or contact Cheryl Ng at +852 2101 0081