senior llm engineer / ai engineer - rag & agentic workflows.

Our client is a forward-thinking technology enterprise in Hong Kong at the forefront of artificial intelligence and digital innovation. They invest heavily in modern AI infrastructure, large language models, and scalable cloud applications, offering a dynamic workplace culture that empowers engineers to deploy impactful, real-world GenAI solutions.

about the team.You will join a high-performing AI & Machine Learning Engineering team comprising data scientists, ML engineers, and platform architects. The team culture is highly collaborative, research-driven, and engineering-focused, providing an ideal environment to experiment with cutting-edge LLM frameworks, optimize model performance, and pioneer agentic system architectures

about the job.

• Design and develop LLM-powered applications, including multi-agent systems, chatbots, and agentic workflows with prompt orchestration and tool/function calling.
• Build advanced Retrieval-Augmented Generation (RAG) capabilities, covering data ingestion, chunking, embedding, vector search, reranking, and citation attribution.
• Develop and maintain robust data pipelines that curate and govern external knowledge sources for LLM applications, ensuring freshness, quality, and access control.
• Improve model and system performance through prompt optimisation, dataset curation, lightweight adaptation (e.g., LoRA/PEFT), and selective fine-tuning.
• Implement and operate LLMOps practices, including deployment, observability, offline/online evaluation, incident response, and latency/cost optimisation.
• Collaborate with ML engineers and software developers to integrate LLM systems into existing products via APIs, microservices, and platforms.
• Track advances in the global LLM ecosystem and translate emerging techniques into measurable production improvements.

skills & experience required.

• Minimum 3 years of hands-on experience developing and deploying production-grade software services and LLM applications.
• Strong proficiency in Python with proven experience building production-grade services, APIs, asynchronous jobs, and automated CI/CD testing pipelines.
• Demonstrated experience with modern LLM frameworks and orchestration tools (e.g., LangChain, LangGraph, LlamaIndex).
• Proven background in RAG tuning, prompt engineering, dataset iteration, or fine-tuning using PEFT/LoRA.
• Strong evaluation mindset with experience measuring groundedness, faithfulness, relevance, win-rate, and running A/B tests.
• Experience deploying AI models in production environments using containers, cloud infrastructure, and scalable architectures.
• Familiarity with AI security practices, privacy, access control, prompt injection defences, and policy-aligned guardrails.
• Degree in Computer Science, Mathematics, Data Science, or a related technical discipline.
• Fluency in English is required; proficiency in Cantonese or Mandarin is an advantage.
• Experience with Kubernetes, cloud-native deployments, or OpenTelemetry observability stacks is highly desirable.

If you are interested in this role, please click 'Apply Now' or send your CV directly to Adyson.yau@randstad.com.hk.