Merge pull request #11 from rajcscw/add-rajkumar-bio

Add Rajkumar Ramamurthy postdoc bio page

Author: tobideusser

assets/rajkumar.jpeg

@@ -0,0 +1,45 @@
+---
+layout: default
+title: Dr. Rajkumar Ramamurthy
+description: false
+---
+
+## About me
+
+![Dr. Rajkumar Ramamurthy](/assets/rajkumar.jpeg){: style="float: right; margin: 0 0 1em 1em; max-width: 250px; border-radius: 4px;"}
+
+I am a Postdoctoral Researcher at the Applied Machine Learning Lab at the University of Bonn since July 2026. I earned my PhD in Computer Science from the University of Bonn in 2023, where my dissertation explored practical models for sequential decision-making in NLP and RL. I am a co-author of [RL4LMs](https://github.com/allenai/RL4LMs), one of the first open-source training frameworks for fine-tuning large language models with reinforcement learning ([paper](https://arxiv.org/abs/2210.01241)).
+
+After my PhD, I worked at several early-stage startups in the US and Germany, where I gained practical experience developing agentic workflows for document-heavy domains and fine-tuning small language models (SLMs).
+
+## Research Interests
+
+My current research interests include, but are not limited to:
+
+- **Agentic Systems:** Developing and benchmarking agentic systems, communication topologies, routing, and orchestration.
+
+- **Harness Optimization / Meta-Harnesses:** Automatically generating harnesses for models and optimizing them continuously from a small set of input-output examples through evolutionary or hill-climbing methods.
+
+- **Model Ensembles / Merging:** Combining multiple models to improve robustness, coverage, and reliability in complex language tasks.
+
+- **Continual Learning:** Enabling models to self-improve from production traces, with or without human feedback.
+
+I am also interested in post-training, benchmarking, and red-teaming.
+
+## Highlighted Publications
+
+[**Google Scholar**](https://scholar.google.de/citations?user=vVzcztcAAAAJ)
+
+*   **Is Reinforcement Learning (Not) for Natural Language Processing: Benchmarks, Baselines, and Building Blocks for Natural Language Policy Optimization**  
+    *Rajkumar Ramamurthy, Prithviraj Ammanabrolu, Kianté Brantley, Jack Hessel, Rafet Sifa, Christian Bauckhage, Hannaneh Hajishirzi, Yejin Choi*  
+    *Proc. ICLR, 2023*  
+    [[Paper]](https://arxiv.org/abs/2210.01241) · [[Code]](https://github.com/allenai/RL4LMs)
+
+*   **Cats Confuse Reasoning LLM: Query Agnostic Adversarial Triggers for Reasoning Models**  
+    *Meghana Arakkal Rajeev, Rajkumar Ramamurthy, Prapti Trivedi, Vikas Yadav, Oluwanifemi Bamgbose, Sathwik Tejaswi Madhusudhan, James Zou, Nazneen Rajani*  
+    *Proc. COLM, 2025*  
+    [[Paper]](https://arxiv.org/abs/2503.01781)
+
+## Contact Details
+
+If you want to get in contact, write an Email to rajkumarramamurthy[at]uni-bonn.de or ramamurthy[at]iai.uni-bonn.de.