Amrita is a PhD candidate at the Data Mining and Machine Learning lab at Arizona State University. Her research primarily focuses on: (i) responsibly leveraging large language models (LLMs) for human-intensive tasks in machine learning pipelines, (ii) safety and robustness of LLMs, (iii) robust detection of AI-generated content. Her work has resulted in over 20 peer-reviewed publications, with ~500 citations, and 3 provisional patent filings. Her work has received recognition via the Outstanding Paper Award at AACL 2023. During her time at NVIDIA NeMo Guardrails, she contributed by proposing a new research direction of inference-time safety steering for LLMs, resulting in a novel framework. Alongside her research, she is actively involved in the community via serving on the Program Committee for multiple conferences such as IJCAI, AAAI, SDM, etc., mentoring students and early career researchers, and speaking about recent developments in AI, GenAI and LLM research.