saikiranpennam

Empirical ML researcher with 2 peer-reviewed publications and active research in mechanistic interpretability and AI safety across cross-modal systems. Hands-on experience designing end-to-end evaluation pipelines from experimental design and adversarial stress-testing through quantitative write-up with a track record of independently scoping experiments and delivering reproducible results within compressed timelines. Experienced in LLM fine-tuning, RAG evaluation architecture, and self-directed project ownership across concurrent research mandates. Currently applying rigorous empirical evaluation methodology to frontier model behavior and AI safety.