Postdoctoral in inference for large language models

Tasks The advertising postdoctoral service is within an ambitious, 5 - Yearly Wallenberg Scholar project titled "Scalable and Adaptive Inferencing for Democratizing Ai". In this project on 18 million, we want to dramatically reduce the costs and energy consumption to serve large language models as chatgpt. More information about the project and our project page with early publications.

The work will primarily include design, implementation and evaluation of distributed systems and networks for machine learning conference. Application of machine learning concepts, with the goal of designing agentic frameworks, will also be included in the project.

As a member of the research group, you will be involved in experimental system work in collaboration with faculty members and several doctoral students at our research lab. You will contribute to scientific publications as well as new grant applications.

The work will be carried out in collaboration with Professor Dejan Kostic and the Senior Lecturer Marco Chiesa.

Qualifications Requirements Departed Doctoral degree or foreign degree that is considered to correspond to a doctoral degree. This authorization requirement must be met at the latest at the time when the employment decision is made.

You should also have a solid background in distributed systems, networks, programming and operating systems and very good knowledge of English in speech and writing when it is required in daily work.

It is important that you have very good knowledge of critical thinking and very good knowledge of C ++, Python, Linux and in any scripting language.

We are looking for a very motivated candidate with the willingness to experiment and explore and who have international publications in magazines and on top conferences.

Merit on the last application date a maximum of three years since the doctoral degree or a foreign degree that is deemed to correspond to the doctoral degree was broken.

Pedagogical ability, as well as awareness of diversity and equal treatment issues with a particular focus on gender equality.

You have good cooperation skills, but can also work independently.

Experience of machine learning, GPU programming or large-scale inference system.

Awareness of diversity and equal treatment issues with special focus on gender equality

We will add great emphasis on personal qualities.

Become a part of KTH KTH, the future forms through education, research and innovation. As a leading international technical university, we play an active role in driving and participating in the transition to a sustainable society. Here you are offered the opportunity to grow and develop in a creative and dynamic workplace with good working conditions and benefits. Gender equality, diversity and equal conditions are a quality issue and an obvious part of KTH's values as a university and state authority.

Read more about our benefits and how it is to work and develop at KTH.

Union representatives Contact information for union representatives.

Application you apply through KTH's recruitment system. You as applicants have the main responsibility for your application complete when submitted.

The application must contain: CV including relevant professional experience and knowledge.

Copy of diplomas and grades from your previous university studies. Translations into English or Swedish if the original documents are not issued in any of these languages.

Brief account of why you want to conduct research, your academic interests and how they relate to your previous studies and future goals. Max 2 pages long.

The application must be received by KTH no later than the last application date at midnight, CET / CEST (Central European Time / Central European Summer Time).

If the employment employment applies until further, however, at the longest two years an employment that postdoctoral is a time-limited merit employment with main focus on research intended as a first career step after defense.

Other for information on the treatment of personal data in connection with recruitment.

It may occur that an employment of KTH is located in a safety class. If this is the case for this particular employment, a security review of applicants is made in accordance with the security law (2018: 585) after consent. In these cases, a prerequisite for employment is that applicants will be approved after security testing.

We abandon us direct contact with staffing and recruitment companies and salesman of job ads.