Aufgaben

• Entwicklung von generativen KI-Modellen zur Abfragegenerierung.
• Zusammenarbeit im Team AI for Data Integration.
• Anwendung von KI-Techniken zur Leistungsbewertung von Datenbanken.

Fähigkeiten

• Master- oder Bachelor-Studium in Informatik oder Ingenieurwesen erforderlich.
• Starke Kenntnisse in ML/AI und Programmierfähigkeiten in Python.
• Kreativität und ausgeprägte Problemlösungsfähigkeiten sind wichtig.

Internship or Master's Thesis

Generative AI Models for Synthetic Query Generation

Ref. 2025_003

A master’s student or intern position is available for a candidate with a passion for bringing innovative gen AI techniques into the world of data platforms and composable data management systems, a positive and problem-solving attitude and the willingness to undertake challenging tasks. The candidate will join for a period of 6 months (internship or master thesis) the group of AI for Data Integration at IBM Research Zurich.

Composable data management systems have been recently proposed by the databse community as the way forward to decouple user workloads (expressed as SQL, low-code/no-code, Python, natural language, etc.) from the various execution engines underneath. To learn which execution engine fits best a user workload, benchmarks like TPC-H or TPC-DS are insufficient, due to their limited number of queries (thus small training set). Our team is working on using gen AI techniques to automatically generate queries that test a database performance in both breadth and depth, are syntactically correct (i.e., they execute on any engine) and they make sense semantically. Ultimately, a successful outcome will push through the limitations of current benchmarks and can be of great interest to the research community. Our team pushes this frontier with a culture of innovation, focusing on the creation and consumption of high-quality science.

Qualifications

• Enrolled or in possession of a Master's degree in computer science or engineering (for master's thesis)
• At least a Bachelor’s degree in computer science or engineering (for internship)
• Strong ML/AI knowledge
• Excellent coding skills, Python preferred
• Familiarity with Linux environments and software development tools (git/GitHub, IDEs, etc.)
• High amount of creativity and outstanding problem-solving ability

Preferred Qualifications

• Experience with LLMs, prompt engineering and tuning, LLM fine-tuning
• Experience with entity linking, schema linking, etc.
• Experience with SQL, TPC-H/-DS benchmarks
• Excellent oral and written English with good presentation skills
• Strong interpersonal skills and excellent written and verbal communication

Diversity

IBM is committed to

diversity

at the workplace. With us you will find an open, multicultural environment. Excellent flexible working arrangements enable all genders to strike the desired balance between their professional development and their personal lives.

How to apply