Manish B.

I am a Lead Data Scientist and Data Engineer with over 10 years of experience turning messy, complex datasets into scalable, high-accuracy predictive systems and automated data pipelines. I specialize in the Retail/FMCG and Healthcare/Pharmaceutical sectors, bridging the gap between advanced technical architecture and actionable business strategy. Backed by an Executive PG in Data Science & AI from IIT Roorkee and holding Microsoft Certifications in Python and Azure (AZ-900 & DP-100), I build the "intelligence layers" that drive enterprise decision-making. My Core Technical Expertise: Data Engineering & ETL: GCP (BigQuery), SQL, dbt, Parquet, Batch Processing, Multiprocessing Programming & AI/ML: Python (Pandas, Scikit-learn, Regex, Flask, Streamlit), R, SAS, Predictive Modeling, GenAI Business Intelligence & Viz: Power BI, Looker, Clinical Dashboards Proven Domain Impact: Retail & FMCG: Engineered automated POS data pipelines (36-month initiative), improving loading efficiency by 30%. Led a 24-month product harmonization project using predictive modeling to resolve discrepancies across millions of records. Designed GCP/BigQuery demand forecasting pipelines to optimize supply chain inventory. Healthcare & Clinical Analytics: Deep experience integrating open-source tools (Python, R, SAS) for clinical trial data visualization. Proficient in building interactive clinical dashboards utilizing Pharmaverse, SDTM, and ADaM datasets. Cloud Architecture & Metrics: Migrated massive datasets to modern cloud environments and developed robust DAU/MAU tracking structures inside BigQuery and Looker. Why Work With Me? I do not just execute code; I solve business problems. Alongside my technical career, I manage my own coworking space business, meaning I inherently understand the commercial urgency, stakeholder management, and extreme ownership required to deliver ROI. Whether you need to deploy an AI model, untangle enterprise ERP data, or build an interactive dashboard from scratch, I write clean, maintainable, and production-ready code. Let’s connect to discuss how we can scale your data infrastructure and build models that actually impact your bottom line.