Join Our Team!

AI-Powered Software Engineering

Our lab focuses on advancing cutting-edge AI technologies and software development techniques to enable innovative problem-solving and real-time collaboration. We specialize in the development of Retrieval-Augmented Generation Small Large Language Models (RAG-sLLM) and Retrieval-Augmented Generation Large Multimodal Models (RAG-LMM), enhancing their effectiveness and adaptability across diverse applications. Additionally, we conduct research in the following areas:

  • Fusion of Intelligent LLM Agents and Community-Based Knowledge: Researching advanced technologies that combine the reasoning capabilities of large language models (LLMs) with community-driven knowledge bases to enable innovative solutions and real-time collaboration in AI and software development.
  • Automated Software Artifact Generation Using sLLM: Leveraging the natural language processing and code generation capabilities of LLaMA3 to develop technology that automates the creation of software artifacts, including requirement definitions, design documents, code, and test cases, throughout the software development lifecycle.
  • Automatic Bug Patch Generation with sLLM: Using LLaMA3's understanding and generation capabilities to automatically detect bugs in source code, analyze the context, and generate appropriate patch code. This research focuses on maximizing software maintenance efficiency, including automating static analysis and code review processes.
  • Issue Template Automation and Collaborative Tool Integration with sLLM: Developing technologies that integrate LLaMA3 with project management tools (such as Open Project, Mattermost, and GitLab) to automate issue template generation and optimize development workflows intelligently.
  • Code Security Issue Detection and Reporting System Using sLLM and DevSecOps: Combining LLaMA3's language understanding capabilities with DevSecOps principles to build high-performance systems that detect and report security vulnerabilities and compliance issues in code in real time.
  • Kubernetes Cluster Setup and Resource Monitoring with sLLM and MLOps: Designing and implementing systems that integrate LLaMA3 with MLOps pipelines to automate Kubernetes cluster setup and efficiently monitor cluster resources and application performance.

Graduate Student Support

  • State-of-the-Art Resources: Access is provided to a powerful kubernetes cluster optimized for scalable and efficient model training and deployment. It features high-performance specifications, including an Intel i9 CPU with 192 cores and 256 threads, 1TB of RAM, and dual H100 GPUs.
  • Personalized Research Space: Each student receives an optimized personal research space, including a high-performance workstation and dual 27-inch LG monitors, supporting a productive and immersive work environment.
  • Financial Support: Comprehensive funding for tuition, living expenses, and annual productivity incentives is provided.
  • Conference and Travel Opportunities: Fully funded participation in leading domestic and international conferences and technical seminars is offered.
  • Knowledge and Career Development: Unrestricted access to IT literature, textbooks, coding tests, portfolio-building resources, and career guidance is provided, focusing on securing positions at top-tier tech companies.
  • Industry Interaction: Opportunities to regularly engage with industry professionals for knowledge sharing and networking are available.

Get in Touch

Lab. website Adviser website

Who Should Apply

  • We are looking for passionate, driven individuals who are eager to collaborate in a cutting-edge research environment and aspire to become leaders in the field of software engineering and development.

Application Details

  • Interested applicants should contact Prof. Geunseok Yang at gsyang@hknu.ac.kr (located in Engineering Building 1, Room 311).

No. of Recruitments

  • We are currently accepting applications for 5 positions: 3 Post-Doctorals and 2 Graduate Students. (April 2025)