AI Engineer: LLMs, RAG, and Autonomous Agents

UST; Penang; On-site; MYR 60,000 - 120,000; Full time

Job summary

UST in Malaysia is seeking an AI/LLM Engineer to develop and optimize AI-powered applications using LLMs and Generative AI. You will design RAG pipelines for intelligent retrieval and build AI agents capable of autonomous reasoning and task execution.

You’ll work with MCP tooling, vector databases, embeddings, and semantic search, and contribute to testing, benchmarking, and documentation across architecture to deployment in cloud environments.

Qualifications

• Bachelor's degree or pursuing final year in Computer Science, Software Engineering, Artificial Intelligence, Data Science, or related fields.
• Familiarity with LLMs and Generative AI concepts.
• Basic Python programming knowledge.
• Understanding of GitHub and software development lifecycle practices.
• Knowledge of REST APIs and system integration concepts.
• Familiarity with prompt engineering and AI application development.
• Strong problem-solving and analytical skills.
• Eagerness to learn emerging AI technologies and frameworks.

Responsibilities

• Develop and enhance AI-powered applications using LLMs and Generative AI technologies.
• Design, implement, and optimize RAG pipelines for knowledge retrieval and QA.
• Build and integrate AI agents capable of autonomous reasoning, planning, and task execution.
• Develop MCP tools to connect AI agents with enterprise systems and databases.
• Assist in evaluating, fine-tuning, and benchmarking LLMs for business use cases.
• Maintain prompt engineering strategies to improve AI response quality and reliability.
• Work with vector databases, embeddings, and semantic search technologies.
• Conduct testing, debugging, and model performance analysis.
• Document technical designs, implementation guides, and AI architectures.
• Support deployment and maintenance of AI services in cloud environments.

Job description

UST in Malaysia is seeking an AI/LLM Engineer to develop and optimize AI-powered applications using LLMs and Generative AI. You will design RAG pipelines for intelligent retrieval and build AI agents capable of autonomous reasoning and task execution.

You’ll work with MCP tooling, vector databases, embeddings, and semantic search, and contribute to testing, benchmarking, and documentation across architecture to deployment in cloud environments.