M.Sc. Computer Science Student / Incoming PhD Applicant / RL Researcher
I am a Master’s student at the University of Stuttgart (Focus: Intelligent Systems, Grade: 1.3) and a Working Student at Porsche AG. My work sits at the intersection of Deep Reinforcement Learning (RL) and Large Language Models (LLMs), specifically focused on making autonomous systems more reliable and interpretable.
🎯 Goal: Currently applying for a PhD starting in 2026, aiming to contribute to ICML, ICLR, and NeurIPS.
- Reinforcement Learning: Generalization in "Learn-to-Optimize" frameworks and high-dimensional black-box optimization .
- ML Systems: Automating verification and validation pipelines in safety-critical automotive environments.
- Anomaly Detection: Scaling LLMs (LogBERT/LogLLM) for zero-shot and few-shot fault detection in complex trace files.
- Master's Thesis (Porsche AG): Deep Learning for Anomaly Detection in Vehicle Control Units.
- Adapted LogBERT and LogLLM for real-world automotive telemetry.
- Demonstrated that scaling from 1B to 8B parameters yields a ~117% improvement in F1-score (0.419 → 0.912) on the BGL dataset.
- Bachelor's Thesis: Parameter-Dependent Self-Learning Optimization.
| Category | Stack |
|---|---|
| RL & Optimization | PPO, SAC, DQN, MCTS, DynaQ+, Policy Gradients |
| Deep Learning | Transformers (LLMs), Diffusion Models, GANs, GNNs, CNNs |
| Languages & Tools | Python, PyTorch, JAX, CUDA, Hugging Face, Scikit-learn, Pandas |
| Engineering | MLOps, CI/CD, Test Case Automation (Porsche), Linux |
- Porsche AG | Working Student (AI/LLM): Automating hardware requirement-to-test case generation using LLMs.
- Porsche AG | Data Science Intern: Discovered ECU fault correlations using Association Rule Discovery.
- University of Stuttgart | Graduate Teaching Assistant: Led tutorials in Data Structures & Algorithms and Theoretical CS (60+ students).
- Baden-Württemberg Scholarship: Semester abroad at the University of Adelaide.
- Business Model Award: Winner for "VectisFinance" in AI Incubator Batch #3.
- AI Software Academy (AISA): Completed Certificate of Advanced Studies (18 ECTS) in AI & Software Engineering.
I'm a practitioner of Strategy Games—Chess, Xiangqi, and Go. I find the algorithmic parallels between MCTS in AlphaZero and human strategic intuition fascinating. 👉 Read my blog post on Mastering the Game of Go
