• To assist the Systems Manager in planning, designing, managing, implementing and supporting AI, Generative AI and related IT projects in the Department;
• To conduct technical studies, proof-of-concept exercises and evaluations of AI technologies, including LLMs, AI computing hardware, software platforms, model serving solutions and open-source AI technologies;
• To perform hands-on installation, configuration, deployment, integration, testing and troubleshooting of AI models and AI-related software components in on-premises, virtualised, containerised or other computing environments;
• To evaluate and deploy LLMs and other AI models, including model selection, model configuration, inference serving, quantisation, model optimisation and integration with application systems and APIs;
• To evaluate AI computing infrastructure and hardware, including CPU, GPU, NPU, memory, storage and network requirements, and to assist in capacity planning, resource sizing and performance optimisation for different AI workloads;
• To assess and make use of suitable open-source AI models, frameworks, libraries and platforms, including evaluation of their technical capabilities, compatibility, licensing, maintainability, security and suitability for departmental use;
• To design, implement and evaluate AI solution architectures, including model serving, retrieval-augmented generation, knowledge bases, vector databases, application integration, AI guardrails and other supporting components where applicable;
• To conduct AI model and system benchmarking, including evaluation of model quality, accuracy, response latency, throughput, concurrency, resource utilisation, scalability and other relevant performance indicators;

‍

• Higher Diploma or above in Computer Science or related subjects
• At least 4 years' experience in IT industry
• At least two (2) years should involve AI, machine learning, Generative AI, or other related technical areas
• Practical and hands-on experience in deploying, configuring, integrating or supporting AI or LLM solutions;
• Good knowledge of LLM technologies and their implementation, including model inference, tokenisation, context handling, prompt processing, model serving, quantisation and performance optimisation;
• Practical knowledge of AI computing infrastructure and hardware, including CPU, GPU, NPU, memory, storage, networking and their impact on AI model deployment and performance;
• Experience with Linux environments, scripting and container technologies, and practical knowledge of deploying applications or AI workloads using containers;
• Experience with programming or scripting languages commonly used in AI development and integration, such as Python, and experience in integrating systems through APIs;
• Knowledge of the open-source AI ecosystem, including open-source LLMs, model repositories, AI frameworks, inference engines and related tools;
• Experience in evaluating AI solutions in terms of functionality, performance, resource utilisation, scalability and suitability for production use;
• Good analytical, problem-solving and troubleshooting skills, with the ability to investigate technical issues across application, model, software and infrastructure layers;

‍