Description

Responsibility

• Develop and optimize Large Language Models (LLMs) application pipelines, including data preparation, prompt engineering, inference and response post-processing.
• Design and build robust LLM-based agents, including tool-use capabilities, planning and memory modules.
• Develop and manage knowledge base and Retrieval-Augmented Generation (RAG) systems for domain-specific information retrieval.
• Collaborate actively with IT, risk, business departments, and external vendors to ensure smooth project advancement.
• Explore and drive the application of new technologies in business operations to promote innovative practices in AI technology.

Requirements:

• Bachelor's degree or higher in Computer Science, Computer Engineering, Information Systems, Statistics, Applied Mathematics.
• Strong proficiency in programming languages such as Python and familiarity with relevant libraries (e.g., PyTorch, Tensorflow, Hugging Face Transformers).
• Proven experience in developing and deploying application using Large Language Models (LLMs).
• Essential abilities in prompting, context engineering, and fine-tuning techniques.
• Experience in developing LLM-based agents and knowledge base/RAG systems.
• Familiarity with model efficiency techniques like LoRA (Low-Rank Adaptation) and knowledge distillation.

If you are applying for in-scope position(s) under the Mandatory Reference Checking Scheme (i.e., A role carrying out regulated activities licensed by the IA, SFC & MPFA), you are required to undergo the Mandatory Reference Checking. Our responsible recruiter will inform you the details of the MRC process and the requirements in due course. For details, please click here .