Aakritii R Gupta

About Aakritii R Gupta

I put data into context. To me, data isn’t just numbers/text in rows and columns — it’s a puzzle waiting to be solved, a story waiting to be told. I love digging into massive, messy datasets, uncovering hidden patterns, and reshaping them into features that actually mean something. Feature engineering is my playground, where raw values become signals and signals become insights. It’s where data stops being abstract and starts speaking in a language decision-makers can understand.Before stepping deep into data science, I worked as a consultant in operational risk and valuation of financial products. That experience taught me how critical precision, transparency, and context are when working with high-stakes data. Whether it’s valuing a derivative or identifying a hidden exposure, I learned how to look beyond the numbers and focus on what they mean in real-world decision-making- Big Data & Processing: Spark, Hadoop- Data Science & ML: RapidMiner, SAS, Google Colab, Predictive Modeling (Random Forest, XGBoost,CatBoost, LightGBM)- Visualization & Storytelling: Tableau- Tools: JIRA, Confluence and GIT- Data Catalog: AlationEmail:

Experience

1. Senior Data Engineer

   PNC

   Mar 2024 — Present · Pittsburgh, PA, US

   Partnered with Product Owners and Business Leads to translate functional requirements into scalable data architectures, ensuring that high-throughput integration pipelines aligned with long-term banking roadmaps- Owned the full production deployment cycle, standardizing release procedures and validation checks to ensure seamless integration of new data features into the live environment- Managed end-to-end project workflows using Jira Kanban to streamline task prioritization and ensure on-time delivery- Facilitated code reviews and benchmarked Spark jobs in lower environments, optimizing execution logic to reduce production runtimes and infrastructure overhead- Architected a modular parallel processing framework for income verification, decomposing complex logic into independent, high-performance tasks; resulted in a 98% reduction in processing time and significantly improved system maintainability- Automated Spark ETL pipelines to detect fraudulent patterns at the loan origination stage, proactively identifying high-risk applications and contributing to a 20% reduction in risky loan exposure- Developed a consolidated credit data mart in a lab environment to support the modeling team in testing creditworthiness and evaluating credit line increase strategies

Education

• Punjab Technical University

  Bachelor of Technology (BTech), Computer Science

  2004 — 2008

• Welingkar Institute of Management

  Post Graduate Diploma in Management, Finance

  2011 — 2013

• Rutgers Business School

  Master's degree, Quantitative Finance

  2017 — 2018