**Introduction** IBM Research takes responsibility for technology and its role in society. Working in IBM Research means you'll join a team who invent what's next in computing, always choosing the big, urgent and mind-bending work that endures and shapes generations. Our passion for discovery, and excitement for defining the future of tech, is what builds our strong culture around solving problems for clients and seeing the real world impact that you can make. IBM's product and technology landscape includes Research, Software, and Infrastructure. Entering this domain positions you at the heart of IBM, where growth and innovation thrive. **Your role and responsibilities** The candidate will work on AI for Code, using large language models (LLMs) to make software developers more productive. More specifically, the role will focus on AI for test-driven development (TDD). While the benefits of TDD are widely accepted, it has struggled with practical adoption due to lack of automation. With the advent of LLMs, we can change that, which should ultimately improve both the speed and quality of software development. The candidate will start by generating reproduction tests from issues, and then expand into other aspects of TDD. Reproduction test generation is a distinct problem statement that differs from traditional test generation because it starts from informal text (the issue description) instead of code, and because the code under test does not yet exist (it only gets written later when the issue is resolved). We have ample evidence that reproduction tests make SWE agents (systems that attempt to automatically resolve issues) more effective. At the same time, reproduction tests also benefit human software developers, since they help developers agree on what the issue is, get them started on resolving it, serve as acceptance criteria for PRs, and become part of a regression test suite to ensure the long-term health of the project. **Required technical and professional expertise** '- large language models - code generation - developer productivity - software engineering research - strong academic publications **Preferred technical and professional experience** '- compiler construction - source code repository mining - prompt tuning for code generation IBM is committed to creating a diverse environment and is proud to be an equal-opportunity employer. All qualified applicants will receive consideration for employment without regard to race, color, religion, sex, gender, gender identity or expression, sexual orientation, national origin, caste, genetics, pregnancy, disability, neurodivergence, age, veteran status, or other characteristics. IBM is also committed to compliance with all fair employment practices regarding citizenship and immigration status.