LLM Adapters for Agentic Workflows- MSC/PHD Student Position- Research Lab

At IBM Research, we are the innovation engine of IBM. Exploring what's next in computing and shaping the technologies the world will rely on tomorrow. From advancing AI and hybrid cloud to pioneering practical quantum computing, we anticipate challenges and unlock new opportunities for clients, partners, and society. Working in Research means joining a team that accelerates discovery at the intersection of high-performance computing, AI, quantum, and cloud. You'l collaborate with leading scientists, engineers, and visionaries to push boundaries and turn ideas into reality. With a culture built on curiosity, creativity, and collaboration, IBM Research offers the opportunity to grow your career while contributing to breakthroughs that transform industries and change the world. At IBM Research, you will work alongside experienced researchers on real technological challenges at the cutting edge of AI. You'll gain hands-on experience, build in-demand technical and professional skills, and contribute to meaningful projects in a collaborative, team-based environment. We are seeking a student to join the IBM Research lab in Beer Sheva and help us build the next generation of AI: Granite Switch. Build AI models like you build software. Our work is open source: https://github.com/generative-computing/granite-switch In this role, you will train and evaluate LLM adapters and apply them to real customer use cases in agentic workloads. You will also develop new ways to switch between adapters quickly and efficiently. Your role and responsibilities: - Work as part of a research team - Break customer agentic workflows down into discrete tasks and tools, and design a specialized adapter for each one - Build datasets for adapter training, including synthetic data generation, data curation and labeling pipelines - Train, fine-tune and evaluate LLM adapters on security-domain tasks - Design benchmarks and evaluation methods that compare Granite Switch with large frontier models on accuracy, latency, cost and data privacy - Build end-to-end proof-of-concept demos showing that Granite Switch solves customer problems better than the alternatives - Analyze results, find where adapters fall short, and iterate on data, training and adapter composition - Present findings to the team and to customers, and contribute to publications, patents and technical blog posts - Contribute code, adapters and benchmarks to Granite Switch and related open-source projects (vLLM, Hugging Face Transformers) - PHD and MSC Students in Computer Science, Software Engineering or Information Systems Engineering - At least one year of studies remaining - Interest in AI, LLMs, data engineering - Advantage: interest and experience in Cyber Security - Advantage: experience working with AI coding agents - Advantage: experience using and contributing to open-source projects Israel Research Hybrid Internship Be'Er Sheva, IL Be'Er Sheva (0692) IBM Israel - Science and Technology Ltd Artificial Intelligence Computer Science Engineering Research Cybersecurity Coding Data Engineering Software Engineering Large Language Model Information Systems