• Successfully delivered a highly ambitious and complicated project of transitioning the Elsevier product’s (Embase) Named Entity Recognition (NER) process to a new machine learning platform.
• Spearheaded comprehensive content quality assessment, identifying and addressing pipeline issues related to taxonomy, entity tagging, and data enrichment. The content quality parameters in NER process were unacceptable, recall & precision metrics being below 60%. With my expertise & domain knowledge, I highlighted all the probable issues and facilitated to achieve a recall of 78% and precision of 86%. This expedited the successful delivery of the project within quality parameters required by product’s minimum acceptance criteria.
• Acted as a liaison between product and tech teams to communicate the specific needs of pharmaceutical and life sciences clients, particularly for Elsevier products Embase & Embiology.
• Hosted timely huddles with the data scientists to address content quality issues, proposing viable solutions, and meticulously defining user stories (JIRA) with clear scope, acceptance criteria, and detailed descriptions.
• Played a pivotal role in prioritizing issues and content-related features for the tech team, expedited releases while upholding high-quality standards across the platform. This accelerated the backlog refinement and final project delivery.
• Ensured accurate data transformations and created feedback loops within cross-functional teams to safeguard the overall data integrity.
2 Page

Family Sabbatical (Childcare)
September 2018 – October 2022
• Utilized this interval for proactive self-development, allocating time to acquire knowledge in diverse areas such as applications of big data in life sciences, fundamentals of machine learning, core IT skills including SQL, SAS, Tableau, among others.
• Engaged in creative writing pursuits, contributing to the creation of short stories, and undertaking a couple of content editing freelance projects.