Iulian Neamtiu

This postdoctoral research associate position is based in the Department of Computer Science at the New Jersey Institute of Technology and is part of an NSF-funded project focused on improving the security of large language model-assisted coding. The successful candidate will work primarily with Professor Iulian Neamtiu and may also collaborate with other CS faculty members. The project develops methods to make AI-generated code safer by combining program analysis and verification with LLM-based code generation. The research aims to express safety and security properties formally, translate those specifications into LLM prompts, and iteratively improve the properties of generated code. The work sits at the intersection of software security, formal methods, and AI-assisted programming. Day-to-day research activities include developing type-and-effect systems and other static and dynamic analyses, building program analysis tools, and integrating those tools into code generation pipelines. The project also involves mining and analyzing large open-source software repositories and using in-house and industrial verification tools. Results are expected to be presented through peer-reviewed publications and professional meetings. The role is a short-term appointment in an active research environment within NJIT’s computing community.