Doctoral student in Large Language Model inferencing KTH Royal Institute of Technology in Sweden

The KTH Royal Institute of Technology invites applications for a doctoral student position in Large Language Model inferencing, as part of the ambitious Wallenberg Scholar project “Scalable and adaptive inferencing for democratizing AI.” This five-year, 18 Million SEK project aims to dramatically reduce the cost and power requirements for serving large language models such as ChatGPT, making advanced AI more accessible and sustainable.

The research will focus on the design, implementation, and evaluation of distributed systems and networks for machine learning inference. The project also involves applying machine learning concepts to develop agentic frameworks, with the goal of advancing scalable and adaptive AI technologies. The position is supervised by Professor Dejan Kostic and Associate Professor Marco Chiesa, both leading experts in distributed systems and networking.

Applicants should have a strong background in computer science, engineering, data science, or machine learning. Knowledge of systems and networking is highly desirable. The position requires a second cycle degree (such as a master's) or equivalent, or at least 240 higher education credits (with at least 60 at second-cycle level). English proficiency equivalent to English B/6 is mandatory. Candidates will be assessed on their ability to work independently, collaborate effectively, and analyze complex issues. Scientific curiosity and a desire to tackle challenging, relevant problems are highly valued.

The doctoral student will be employed full-time for up to four years, with a monthly salary according to KTH’s Doctoral student salary agreement and access to employee benefits. The position offers a creative and dynamic research environment at one of Europe’s leading technical universities, with opportunities for professional growth and development. Equality, diversity, and equal opportunities are integral to KTH’s core values.

To apply, candidates must submit a complete application through KTH’s recruitment system, including certified copies of diplomas and grades, proof of language requirements, CV, application letter (maximum two pages), and representative publications or technical reports. Applications must be received by the deadline, 2026-04-30. For further information about doctoral studies at KTH and the project, please refer to the official KTH website and project page.

Join KTH and contribute to cutting-edge research in scalable and adaptive AI inferencing, helping to shape the future of technology and society.