Rolf Jagerman

About me

I'm a senior software engineer at Google DeepMind's GenAI Unit where I focus on Large Language Models + Ranking.

My research interests include ML infrastructure, Large Language Models, Learning-to-Rank and Counterfactual Learning. I am the lead developer of RAX, a library for Ranking in JAX. I've also actively contributed to open-source software such as TF-Ranking and JAX.

My research has resulted in over 20 publications across top conferences (NeurIPS, KDD, SIGIR, WSDM, NAACL, etc.). My applied research has powered launches across Google products, including YouTube, Google Cloud AI and Chrome Web Store.

Before joining Google I obtained my PhD at the University of Amsterdam, my MSc at ETH Zürich and my BSc at Delft University of Technology.

You can download my CV here.

Open Source Projects

Rax: Composable Learning-to-Rank using JAX.

PyTorchLTR: Learning-to-Rank in PyTorch.

Glint: Spark-compatible parameter server.

Publications

H. Oosterhuis, R. Jagerman, Z. Qin, X. Wang and M. Bendersky, Reliable Confidence Intervals for Information Retrieval Evaluation Using Generative A.I.. KDD, 2024.

Z. Qin, R. Jagerman, K. Hui, H. Zhuang, J. Wu, L. Yan, J. Shen, T. Liu, J. Liu, D. Metzler, X. Wang and M. Bendersky, Large Language Models are Effective Text Rankers with Pairwise Ranking Prompting. NAACL, 2024.

Z. Qin, R. Jagerman, R. Pasumarthi, H. Zhuang, H. Zhang, A. Bai, K. Hui, L. Yan and X. Wang, RD-Suite: A Benchmark for Ranking Distillation. NeurIPS, 2023.

R. Jagerman, H. Zhuang, Z. Qin, X. Wang and M. Bendersky, Query Expansion by Prompting Large Language Models. Gen-IR, 2023.

A. Bai, R. Jagerman, Z. Qin, P. Kar, B. Lin, X. Wang, M. Bendersky and M. Najork, Regression Compatible Listwise Objectives for Calibrated Ranking. arXiv, 2022.

H. Zhuang, Z. Qin, R. Jagerman, K. Hui, J. Ma, J. Lu, J. Ni, X. Wang and M. Bendersky, RankT5: Fine-Tuning T5 for Text Ranking with Ranking Losses. arXiv, 2022.

R. Jagerman, X. Wang, H. Zhuang, Z. Qin, M. Bendersky and M. Najork, Rax: Composable Learning-to-Rank using JAX. KDD, 2022.

R. Jagerman, Z. Qin, X. Wang, M. Bendersky and M. Najork, On Optimizing Top-K Metrics for Neural Ranking Models. SIGIR, 2022.

Z. Qin, H. Zhuang, R. Jagerman, X. Qian, P. Hu, C. Chen, X. Wang, M. Bendersky and M. Najork, Bootstrapping Recommendations at Chrome Web Store. KDD, 2021.

R. Jagerman, W. Kong, R. Pasumarthi, Z. Qin, M. Bendersky and M. Najork, Improving Cloud Storage Search with User Activity. WSDM, 2021.

R. Jagerman, Efficient, Safe and Adaptive Learning from User Interactions. PhD Thesis, 2020.

R. Jagerman and M. de Rijke, Accelerated Convergence for Counterfactual Learning to Rank. SIGIR, 2020.

R. Jagerman, I. Markov and M. de Rijke, Safe Exploration for Optimizing Contextual Bandits. TOIS, 2020.

R. Jagerman, H. Oosterhuis and M. de Rijke, To Model or to Intervene: A Comparison of Counterfactual and Online Learning to Rank from User Interactions. SIGIR, 2019.

R. Jagerman, I. Markov and M. de Rijke, When People Change their Mind: Off-Policy Evaluation in Non-stationary Recommendation Environments. WSDM, 2019.

R. Jagerman, K. Balog and M. de Rijke, OpenSearch: Lessons Learned from an Online Evaluation Campaign. JDIQ, 2018.

R. Jagerman, K. Balog, P. Schaer, J. Schaible, N. Tavakolpoursaleh and M. de Rijke, Overview of TREC OpenSearch 2017. TREC, 2017.

R. Jagerman, H. Oosterhuis and M. de Rijke, Query-level Ranker Specialization. LEARNER, 2017.

R. Jagerman, J. Kiseleva and M. de Rijke, Modeling Label Ambiguity for Neural List-Wise Learning to Rank. Neu-IR, 2017.

R. Jagerman, C. Eickhoff and M. de Rijke, Computing Web-scale Topic Models using an Asynchronous Parameter Server. SIGIR, 2017.