• I am doing a research internship in Redmond with the Microsoft Gray Systems Lab this summer.
• Sebastian, Shubha and me won an ACM SIGMOD Best Demo Runner Up Award for our demo on Proactively Screening Machine Learning Pipelines with ArgusEyes.
• We open-sourced our prototype StreamDQ, a library built on top of Apache Flink for defining “unit tests for data”, which measure data quality in large data streams.
• Our poster on Provenance Tracking for End-to-End Machine Learning Pipelines and a presentation on Data Distribution Debugging in Machine Learning Pipelines have been accepted for ProvenanceWeek2023.
• Our demo on Proactively Screening ML Pipelines with ArgusEyes was accepted at SIGMOD.
• Our paper on Automating and Optimizing Data-Centric What-If Analyses on Native Machine Learning Pipelines has been accepted at SIGMOD! Very excited to finally present mlwhatif in this paper!
• I gave an in-depth talk about the inner workings of mlinspect at the Dutch Seminar on Data Systems Design.
• Our paper Towards Data-Centric What-If Analysis for Native Machine Learning Pipelines has been accepted for the DEEM workshop at SIGMOD! In this vision paper, we present our initial ideas for my next research project.
• Our paper on Data Distribution Debugging in Machine Learning Pipelines was accepted for the VLDB Journal Special Issue on Data Science for Responsible Data Management! This work is part of our ongoing collaboration with Julia Stoyanovich from NYU.
• Our abstract ArgusEyes: Screening Native Machine Learning Pipelines was accepted at the Dutch-Belgian Database Day.
• Our abstract on Screening Native Machine Learning Pipelines with ArgusEyes will be presented at CIDR’22. This is joint work with Ce Zhang from ETH Zuerich.
• Sebastian and me gave a talk on Data Provenance as the Foundation for Data Governance at the virtual Data Centric AI workshop organised by Stanford and ETH Zuerich.
• We presented our work on mlinspect at the ICAI Lunch Meetup.
• mlinspect will be used for NYU’s course on Responsible Data Science to teach students about the importance of data preprocessing, making data distribution debugging part of their methodological toolkit.
• We will present a demo on a data distribution debugger for machine learning pipelines and a paper on maintaining randomized trees for low-latency machine unlearning at SIGMOD 2021.
• I joined UvA as Ph.D. student to work on data validation for ML pipelines.
• We presented our work on Lightweight Inspection of Data Preprocessing in Native Machine Learning Pipelines at CIDR. Checkout the video of our talk and our example notebook!
• We presented our work on mlinspect at the Dutch-Belgian Database Day.

I am a Ph.D. student at the University of Amsterdam in the Intelligent Data Engineering Lab, conducting research at the intersection of data management and machine learning. I mainly publish at conferences like SIGMOD and VLDB.

My Ph.D. advisors are Sebastian Schelter and Paul Groth. I work on responsible data management (also in collaboration with Julia Stoyanovich). Before my Ph.D., I did my masters at TU Munich with Thomas Neumann and Alfons Kemper and focused on databases.

During my studies, I interned with Microsoft GSL, Amazon Research, Oracle Labs, and worked as a research assistant at TU Munich. I also interned and worked as a working student at TNG Technology Consulting in Munich and worked as a teaching assistant at University of Augsburg.

In the past, I have been working on deequ, a library for ‘unit-testing’ large datasets with Apache Spark, PGX, an in-memory graph analytics framework, and Umbra, a disk-based database with in-memory performance. Currently, I work on mlinspect and mlwhatif. The goal is to diagnose and mitigate robustness and reliability issues in machine learning pipelines.