Research Engineer II (Trust Technologies) - LLM AI Agents for Insurance

About the role

The National Centre for Research in Digital Trust (DTC) at Nanyang Technological University is looking for a Research Engineer to build LLM-powered AI agents that automate and improve insurance workflows such as underwriting, claims, policy servicing, risk assessment and customer engagement. You will create autonomous and multi-agent systems that read insurance documents, apply policy rules, support human decision-making and execute end-to-end processes safely.

Key responsibilities

• Translate fluently between business and technical contexts so stakeholders, engineers and insurance partners understand complex AI, LLM and agentic AI concepts.
• Research LLM-powered AI agents and multi-agent systems, turning algorithms, tools and frameworks into working prototypes that show how research can become new insurance capabilities.
• Work with Centre researchers to design and develop production-oriented implementations for underwriting, claims, policy servicing and risk assessment.
• Design and build agent tools, evaluation frameworks and demonstration environments that enable technology transfer to research partners.
• Produce and maintain technical documentation, presentations and research papers on AI agent design, evaluation, guardrails and trust mechanisms.
• Engage global partners and researchers to track trends in LLMs, agentic AI and InsurTech and strengthen Singapore's thought leadership in trustworthy AI agents for insurance.

Required profile

• Master's degree in Computer Science, Artificial Intelligence, Data Science, Software Engineering or a related discipline; prior research or engineering experience in LLMs and AI agents is preferred.
• Ability to translate fluently between business and technical contexts.
• Experience in insurance, financial services or other regulated domains is preferred, especially applying LLM-based agents to underwriting, claims, policy servicing, risk assessment and customer engagement.

Required skills

• Strong hands-on experience with large language models, prompt engineering, retrieval-augmented generation, agent frameworks and multi-agent system design.
• Proficiency in Python and common AI/ML tools, with experience building production-grade AI applications, APIs, evaluation pipelines and agent orchestration systems.
• Solid understanding of AI safety, guardrails, model evaluation, monitoring, data privacy, explainability and responsible AI in regulated environments.
• Good knowledge of system platform development, database technologies and software engineering best practices.