- Multi-agent coordination systems for real-time network optimization (Master's thesis)
- LLM tool-use integrations with structured outputs and validation layers
- Reproducible ML experiment pipelines and evaluation workflows
- Robust data validation and quality checks for ML pipelines
- Planning and reasoning strategies in agentic systems
- RAG pipeline design and retrieval evaluation
- Designing reproducible ML experiments
- Turning research prototypes into working tools
- Running local LLMs (Ollama) for practical tasks
- Python data workflows and ETL pipelines
Built my first LLM agent on a 5G testbed. Still not sure which part was harder.
