The TIB is a foundation of public law of the Land of Lower Saxony. With around 600 employees and an budget of around 60 million euros, it is one of the largest information infrastructure facilities in Germany. The TIB ensures optimal working conditions and continuously expands measures for the reconciliation of work and family life. It wants to promote equality between women and men in particular and therefore urges special qualified women to apply. Applications for people with severe disabilities and people with equal status are preferably taken into account with the same suitability. If you would like your rights to be considered as a severely disabled person or as a seriously disabled person of equalized person in the selection procedure, we ask you to inform us of this voluntarily in your application (e.g. in writing or in the CV or elsewhere clearly highlighted) and to add a corresponding proof (e.g. copy of the severely disabled ID). We are pleased to receive applications from all nationalities. Equal opportunities is one of our central organizational values. We are therefore pleased to receive applications regardless of nationality, ethnic and social origin, sexual identity, sexual expression and/or sexual feature, religion and belief, age as well as sexual orientation and identity. Please indicate in the subject of your application which job exchange you have become aware of our offer. We would like to point out that application documents are not sent back in principle. Job alert No 16/2026; Application deadline: 14.06.2026 As a German Central Library of Technology and Natural Sciences, our pioneering services ensure the infrastructural requirements of high-quality information and literature supply for research in science and industry. With the Open Research Knowledge Graph (ORKG), we work to revolutionize the exchange and use of scientific knowledge in the digital age. The Technical Information Library (TIB), Programme D, Open Research Knowledge Graph, , is looking for the research group AI for Scholarly Communication (Prof. Dr. Sahar Vahdati) on 1st. September 2026 a:n Senior KI/ML Engineer or Postdoc / Scientific:r Staff:in – LLM Infrastructure (m/w/d) The job is limited to the project duration of three years. An extension is possible. Regular weekly working hours are 39.8 hours (full time). In principle, the workplace is part-time. The activity is to be carried out in principle at the Hanover site. Mobile work is possible in proportion to the needs of the service. The grouping takes place in the remuneration group 13 TV-L.

We are looking for a senior AI/ML engineer with interest in building, optimizing and operating scalable, universally applicable AI assistants in the ecosystem of the European Open Science Cloud (EOSC). The successful applicant has a well-founded knowledge in the field of machine learning and artificial intelligence, a solid mathematical understanding and practical experience with the optimization of LLM interference in cloud environments. The focus of the activity is on scalable training and inference pipelines, token efficiency and model selection strategies, distributed ML systems in productive use and evaluation of open models. In addition, the activity includes the optimization of latency, cost and performance balances, the support of parameter-efficient adaptation workflows as well as the reliable integration into orchestration layers in EOSC service environments. Your activity includes Conception and development of inference infrastructures in cloud environments with continuous optimization of latency, throughput and cost efficiency Benchmarking of models based on task-specific and general evaluation criteria as well as deriving data-based recommendations for model-task fit Application of quantization, distillation, parameter-efficient fine tuning and further optimization techniques to improve efficiency, performance and cost efficiency Building an orchestration layer that seamlessly integrates into the cross-border agent framework and supports new AI protocols such as MCP, A2A and ACP Integrating Observability from the start using tools such as OpenTelemetry and Grafana to visualize model performance, cost and reliability transparent, measurable and operationally

Completed academic studies (master or equivalent degree) in computer science, software engineering, artificial intelligence, data science or a related subject Proven experience with the optimization of LLM interference in cloud environments Practical experience with fine tuning, quantization, parameter-efficient fine tuning (PEFT) and the provision of large language models in productive or production-related environments Experience with model profiling, benchmarking and defining performance baselines Experience in the design, development or operation of scalable training and inference pipelines in distributed AI/ML systems Knowledge of multi-agency systems, agentic workflows or orchestration frameworks such as LangGraph or AutoGen Experience in dealing with open source LLMs such as Llama or Mistral Very good programming knowledge in Python as well as experience in the development of reproducible codes, for example with PyTorch or comparable frameworks Good knowledge of cloud-native technologies, in particular Docker and Kubernetes Very good English skills in word and writing Required qualifications Completed doctorate in a relevant field Experience with agentic design patterns, such as reflection, ranking, exploration/discovery or human-in-the-loop feedback loops Experience in dealing with scientific datasets and in the application of FAIR principles to data, model results or research workflows Embossed written communication skills and experience in interdisciplinary cooperation, including contributions to scientific publications Knowledge of the programming language Rust

Our aim is to rethink and innovate the provision and use of research data and information. In the TIB research and development department, you have the opportunity to advance your scientific further qualification and research career in a dynamic and excellent research environment. We offer an intellectually inspiring environment with entrepreneurial thinking, embedded in a leading technical university and one of the largest information centres in the Leibniz community. With the L3S research centre at Leibniz Universität Hannover, one of the world's leading research institutes in the field of Web & Data Science, there is a close cooperation within the framework of the Leibniz Joint Lab Data Science & Open Knowledge. Last but not least, we value an open and creative working environment where it is fun to work. In addition, we offer A community-oriented workplace in public service based on the TV-L with a remuneration according to the remuneration group 13 TV-L A special payment at the end of the year and 30 days holiday a year at a five-day week as well as additional free days on Christmas Eve (24.12.) and New Year's Eve (31.12.) A flexible workplace in time and space with offers for the reconciliation of work and family, such as mobile work and flexible working time models (guiding time) A modern workplace in a central location of Hanover with a collegial, attractive and versatile work environment An employer with a wide range of continuing and continuing training, occupational health promotion and pension provision for public service (VBL) Employee discount in the students of the Studentenwerk Hannover as well as the possibility to use the versatile offers of the University Sports Hannover Individually responsible and forward-looking activities that offer variety and leave room for personal development Financing of necessary equipment and conference participations and research stays Cooperation in national, European and international research and innovation projects