The DEEM Lab is a research group at the Berlin Institute for the Foundations of Learning and Data (BIFOLD), led by Prof. Dr.-Ing. Sebastian Schelter. Our lab conducts fundamental research at the intersection of data engineering and machine learning. We design novel data infrastructure and systems for AI workloads, with the goal of lowering the technical bar to efficiently and responsibly work with data. The focus areas of the lab are:

• Data management for AI and data science, with a focus on synthesizing, optimizing and debugging machine learning pipelines
• Data processing in compliance with legal regulations, such as the “right-to-be-forgotten”

Our research is accompanied by efficient and scalable open source implementations, many of which are applied in real world use cases, for example in the Amazon Web Services cloud and in large European e-commerce platforms. Our students regularly go on industry internships, for example with the Gray Systems Lab of Microsoft or Amazon Research. Our research contributions have been recognized with an ACM SIGMOD Systems Award, an ACM SIGMOD Best Demo Runner Up Award, a Best Paper Runner Up Award from the Table Representation Learning workshop at NeurIPS, and industry awards such as an Amazon Education Research Grant Award and the Olympus Mons Pioneer Award. We have ongoing collaborations with researchers from the University of Amsterdam in the Netherlands, and New York University in the US.

• Apr 22, 2026 ‐ Arnab has been selected for one of the runner ups for this year’s ACM SIGMOD Jim Gray Dissertation Award, which recognizes excellent research by doctoral candidates in the database field! This distinction is only given to a small number of PhD dissertations worldwide each year.
  
  
• Mar 15, 2026 ‐ The benchmark paper SemBench: A Benchmark for Semantic Query Processing Engines has been accepted for publication at VLDB’26. This is the result of a collaboration between Google’s BigQuery team and researchers from Cornell, MIT, UTN, UMichigan, and our lab, driven by Olga from our side. Checkout sembench.org for the latest leaderboard and results!
  
  
• Dec 16, 2025 ‐ Arnab’s 2025 paper, MEMPHIS: Holistic Lineage-based Reuse and Memory Management for Multi-backend ML Systems, has received the prestigious SIGMOD Research Highlight Award and will appear in the March 2026 special issue of SIGMOD Record. The paper has previously won the EDBT 2025 Best Research Paper Award.
  
  
• Nov 3, 2025 ‐ Barrie has been invited to submit an extended version of his paper on Scalable Data Debugging for Neighborhood-based Recommendation with Data Shapley Values to the Special Issue on Highlights of RecSys ’25 of the ACM Transactions on Recommender Systems.
  
  
• Sep 26, 2025 ‐ Barrie and Pierre are at RecSys in Prague this week! Barrie presents our work on on Scalable Data Debugging for Neighborhood-based Recommendation with Data Shapley Values, which was selected as a spotlight oral. Pierre gives a talk on his initial ideas Towards a Real-World Aligned Benchmark for Unlearning in Recommender Systems at the Responsible recommendation workshop.
  
  

Faculty, Postdocs & Staff
Prof. Dr. Sebastian Schelter	Dr. Arnab Phani	Celia Bohnhardt-Schneider	Wilbert Wiryadi
PhD Students
Zeyu Zhang	Hao Chen	Olga Ovcharenko	Pierre Lubitzsch
Anna Richter	Leonardo Dominici	Elias Strauss
Student Assistants
Aram Al Jnasdi	Tim Schuster
Guest Researchers
Dr. Stefan Grafberger (Snowflake)	Shubha Guha (University of Amsterdam)	Till Doehmen (Motherduck)	Yichun Wang (University of Amsterdam)

• Dr. Stefan Grafberger, PhD student, Software engineer at Snowflake
• Dr. Barrie Kersbergen, PhD student, Staff scientist at bol.com
• Dr. Olivier Sprangers, PhD student, Applied scientist at Nixtla
• Dr. Mozhdeh Ariannezhad, PhD student, ML scientist at booking.com
• Dr. Arezoo Sarvi, PhD student, Data scientist search at Albert Heijn
• Aynaz Abdollahzadeh, Master student, Data engineer at Churned
• Radu Geacu, Master student, Data engineer at the Royal Schiphol Group
• David Vos, Master student, PhD student at the University of Amsterdam
• Benjamin Wang, Master student, ML scientist at booking.com
• Dr. Ji Zhang, Guest researcher, Research scientist at Huawei

Sebastian Schelter is a Full Professor at the Berlin Institute on the Foundations of Learning and Data (BIFOLD) and Technische Universität Berlin. His research focuses on the intersection of data engineering and machine learning, with the goal of lowering the technical bar to efficiently and responsibly work with data.

The research of his group is accompanied by efficient and scalable open source implementations, many of which are applied in real world use cases, for example in the Amazon Web Services cloud and in large European e-commerce platforms.

In the past, he has been an assistant professor at the University of Amsterdam, a faculty fellow at New York University, a senior applied scientist at Amazon Research and a research intern at Twitter and IBM Almaden in California. His research contributions have been recognized with an ACM SIGMOD Systems Award, an ACM SIGMOD Best Demo Runner Up Award, and a Best Paper Runner Up Award from the Table Representation Learning workshop at NeurIPS.

• Email: schelter[at]tu-berlin[dot]de
• Profiles: Google Scholar, Linkedin, DBLP, ORCID
  
  

Summer semester 2026

We offer the following courses during the summer semester 2026:

• Machine Learning Model Management and Inference
• Project on Data Engineering for AI & ML
• Seminar on Data Engineering for AI & ML
• Programming Practical on Data Systems: Machine Learning Pipelines
• Programming Practical on Data Systems: Fairness Auditing
• Research Seminar on Data Engineering for AI & ML (available to students writing a thesis with us)

For taking one of our courses, please sign up on the corresponding course page on ISIS and attend the first lecture, where we will discuss the details for the formal registration.

Theses

If you are interested in writing a bachelor or master thesis with us, please check out our list of available topics and consult our information on the logistics of writing a thesis with us. Below is a selection of recently completed theses in our lab:

• Automatic optimization of agent-generated machine learning pipelines (Elias Strauss)
• Multi-modal datasets for cross-modal error detection: integrating tabular and visual data (Luciano Duarte)
• End-to-end machine unlearning through data preparation pipelines and feature stores (Leonardo Dominici)
• Towards fair database access: detecting and mitigating social bias in NL2SQL systems using reinforcement learning (Aynaz Abdollahzadeh)
• Robust and dialect-independent parsing of schema information from SQL scripts (Radu Geacu)
• Language control prefixes: conditional prefix-tuning for efficient multilingual data-to-text generation in low-resource languages (David Vos)
• Understanding the characteristics and robustness of data preparation pipelines for machine learning (Jialin Dong)
• Towards amnesiac recommender systems: efficient incremental and decremental updates for next basket recommendation (Benjamin Wang)
• Efficient lineage-based inspection of machine learning pipelines (Stefan Grafberger)

2x Student employees (40h/month each)

We are looking for two dedicated and responsible student research assistants to support our lab members in their research activities, please see https://github.com/deem-data/student-assistants/blob/main/topics.md for detailed information on the research focus areas and projects. The student assistants will review relevant literature and implementations, assist with the implementation and documentation of features, and help with writing tests and benchmarks. They will be included as a co-author on the resulting scientific publications.

Requirements

• Extensive knowledge of machine learning models and workflows
• Proficiency in Python, using libraries such as NumPy, Pandas, or PyTorch
• Experience with open-source development practices or contributions to open-source projects
• Experience writing clean, modular, and well-documented Python code
• Willingness to perform the work primarily on the TU Berlin campus

Not required, but helpful

• Research experience in machine learning or data systems
• Good knowledge about popular agentic systems for ML engineering

Please submit your written application including cover letter, your CV, certificate of enrollment, and current transcript of records, as a single PDF file with the reference number IV-SB-0036-2026 to sekr [at] deem [dot] tu-berlin [dot] de until 22nd of July 2026.

Email: sekr[at]deem[dot]tu-berlin[dot]de

Technische Universität Berlin
FG Management of Data Science Processes
Sekr. FR 7-3
Franklinstr. 28 / 29
10587 Berlin
Germany

Responsibility under the German Press Law §55 Sect. 2 RStV:
Prof. Dr.-Ing. Sebastian Schelter