Atita Arora is a seasoned and esteemed professional shaping the landscape of information retrieval systems. Her open source track record includes work as a committer on a range of information retrieval and relevancy workbench projects, notably Apache OpenNLP and Quepid, alongside an open source implementation called Chorus and widely read blog posts on leveraging vectors in e-commerce search.

At the heart of her work is a simple but demanding question: what makes a search or retrieval system good? Atita approaches that question through OTB metrics and user-centric approaches, calibrating systems against what users actually experience rather than what benchmarks alone suggest. Her perspective is informed by the full arc of the field, from the Solr and Lucene era through today’s vector databases and LLM-powered retrieval, and her current research focuses on evaluating retrieval-augmented generation (RAG) systems end to end, including chunking and embedding strategies, prompt design, citations, and multi-level evaluation with humans in the loop to keep problems like hallucination in check.

Beyond the technology, Atita is a fervent believer in diversity and inclusion. She actively champions initiatives to foster inclusivity in search and data science, proudly represents the Women of Search Group, and participates in various DEI forums, working to create a more inclusive environment in tech while continuing to drive innovation in information retrieval.