AI Engineer: LLM Orchestration & RAG Pipelines

PERSOL; Hong Kong; On-site; HKD 600,000 - 900,000; Full time

Job summary

PERSOL is seeking an AI Engineer to design, develop, and maintain scalable AI applications for NLP and computer vision. You will build RAG pipelines, integrate LLMs, and deploy solutions in cloud environments with a focus on reliability and scalability.

You will work with LangChain, LlamaIndex, and Semantic Kernel, applying containerization via Docker/Kubernetes, and collaborate with cross-functional teams to deliver production-grade AI workflows.

Qualifications

• Bachelor’s or Master’s degree in Computer Science, Data Science, Engineering, or a related discipline.
• 1+ years of experience in AI engineering, ML, or software development involving AI systems.
• Proven experience building end-to-end AI applications or ML systems in production.
• Strong experience with cloud platforms (Azure preferred) for deploying AI workloads.
• Hands-on experience with Azure OpenAI, Azure AI Search, or similar technologies for LLM-based systems.
• Experience with LLM frameworks such as LangChain, LlamaIndex, or Semantic Kernel.
• Strong programming skills in Python for AI/ML development and system integration.
• Experience with Docker and Kubernetes for containerization/orchestration.
• Strong problem-solving and communication skills in cross-functional environments.

Responsibilities

• Design, develop, and maintain scalable AI applications and ML models for NLP and CV use cases.
• Build and optimize Retrieval-Augmented Generation pipelines using vector-based systems.
• Engineer agentic AI workflows with multi-step reasoning, tool-calling, orchestration, and memory management.
• Develop end-to-end AI systems covering architecture design, model integration, and cloud deployment.
• Work with LLM orchestration frameworks to build production-ready AI workflows.
• Perform performance evaluation, tuning, A/B testing, and monitoring of AI systems in production.
• Deploy and manage AI solutions using Kubernetes or OpenShift for scalability and reliability.
• Research emerging AI concepts to enhance system interoperability.
• Collaborate with cross-functional teams to integrate AI into web and mobile apps.
• Produce technical documentation, participate in code reviews, and uphold engineering best practices.

Skills

Python programming

Problem solving

Communication skills

ML system design

Education

CS/DS/Engineering degree

Tools

Azure OpenAI

Azure AI Search

LangChain

LlamaIndex

Semantic Kernel

Docker

Kubernetes

Job description

PERSOL is seeking an AI Engineer to design, develop, and maintain scalable AI applications for NLP and computer vision. You will build RAG pipelines, integrate LLMs, and deploy solutions in cloud environments with a focus on reliability and scalability.

You will work with LangChain, LlamaIndex, and Semantic Kernel, applying containerization via Docker/Kubernetes, and collaborate with cross-functional teams to deliver production-grade AI workflows.