At IBM work is more than a job - it’s a calling: To build. To design. To code. To consult. To think along with clients and sell. To make markets. To invent. To collaborate. Not just to do something better, but to attempt things you’ve never thought possible. Are you ready to lead in this new era of technology and solve some of the world’s most challenging problems? If so, let’s talk.
We’re part of the Language Technologies theme in IBM Research. The theme develops innovations in areas like AI-agent evaluation, monitoring and analytics, large-scale data processing for AI, and retrieval/search systems. These innovations become real IBM products used by customers, and the teams also publish papers and file patents.
Our group focuses on advanced retrieval for AI agents: building methods that let agents pull information from structured data (SQL/JSON) and unstructured data (text, tables, images), correlate between sources, and generate reliable answers. It’s a place where strong researchers work together, and a great environment to grow.
You’ll work with senior researchers on new retrieval methods for LLM-based systems, such as:
• Implementing and testing retrieval pipelines
• Exploring hybrid retrieval over structured + unstructured sources
• Helping design multi-step agentic retrieval flows
• Running experiments, analyzing results, and supporting benchmark creation
• Contributing ideas to improve accuracy, speed, and robustness
• MSC/PHD Student in CS / Software Engineering / Information Systems
• Strong coding skills and passion for AI
• Python experience
• Experience with LangChain or LLM tooling – advantage
• RAG knowledge – advantage
• Curiosity, initiative, and willingness to explore
Please add your grade sheet to your application
Publication/s at top-tier peer-reviewed conferences or journals.