ATMRI at NTU is seeking a Research Fellow to join the Digital ATCO Assistant project. The role focuses on leading the assistant’s knowledge, retrieval, reasoning, and agent orchestration capabilities through LLMs, Agentic AI, multi-agent architectures, and Retrieval-Augmented Generation.

Responsibilities:

• Design, develop, and evaluate Agentic AI and multi-agent architectures for task decomposition, planning, reasoning, coordination, and workflow orchestration within the Digital ATCO Assistant project.
• Develop tool/function calling capabilities that enable agents to select and invoke tools, APIs, and knowledge services, including input validation, interpretation of tool outputs, and error handling.
• Develop the retrieval agent and end-to-end RAG pipelines across AIPs, NOTAMs, operational procedures, and regulations using vector databases, semantic retrieval, and knowledge graphs or structured knowledge representations.
• Design benchmarks and conduct experiments to evaluate agent task performance, multi-agent coordination, tool-call correctness, retrieval precision/recall, factuality, grounding, and hallucination.
• Work with the integration engineer/technical lead to expose agent, retrieval, and reasoning capabilities through APIs and microservices for integration into the prototype.
• Work with domain experts and controllers to translate operational use cases into research requirements, evaluation datasets, and test scenarios.
• Contribute to technical reports, project proposals, publications, demonstrations, and collaboration with academic, industry, and regulatory partners.

Requirements:

• PhD in AI, Computer Science, Machine Learning, NLP, or a related discipline; or a Master’s degree with substantial applied research experience.
• 2-4 years hands-on experience with LLM, Agentic AI, multi-agent architectures, tool/function calling, and prompt/context engineering.
• Experience with RAG, vector databases, semantic retrieval, knowledge graphs or structured knowledge representation, grounded generation, and hallucination mitigation.
• Strong Python skills and experience with PyTorch, modern LLM frameworks, APIs, microservices, and evaluation of retrieval precision/recall and factuality.
• Experience with LoRA/PEFT, in-context learning, Graph RAG, temporal RAG, hybrid symbolic-neural reasoning, on-premise deployment, or inference optimisation is highly desirable.
• Good communication and multidisciplinary collaboration skills; relevant peer-reviewed publications and experience in safety-critical domains are preferred.

We regret to inform that only shortlisted candidates will be notified.