Headline

Data Engineer II - Python, SQL, BigQuery, Statistics, Open to Data Engineering & AI/ML Roles

About

Data Engineer II at Bayer | Statistics-Trained | Python, SQL, BigQuery, dbt, Airflow, AWS Combining a statistics background with hands-on engineering to turn ambiguous problems into reliable analytics, six years of delivering across statistics, ML, and data engineering, for stakeholders ranging from engineers to global leadership. A few things I've worked on: Led development of a Python Dash application that replaced a legacy reporting system across 62 cost centers and 362 users globally, saving ~$300K/year while improving data reliability. Traced a ~$1M cost discrepancy across countries and cost centers to a flawed conversion metric, using a Power BI report I built to surface the issue and correct budget reporting. Built a binary classification model (XGBoost, KNN) at 91% accuracy on 100,000+ protein sequences, visualized in Power BI to support real nomination decisions for a global Biologics team. Automated BigQuery/dbt pipelines with CI/CD via GitHub Actions, and built a retrieval-augmented QA system using LlamaIndex and Gemini as an early exploration into applied GenAI. Open to data engineering and applied analytics roles.

Location

India

AI stack

claude code

cursor

gemini

Work experience

Data Engineer II at Bayer, Apr 2026 - Present · 5 mos, Built scalable AWS ETLT pipelines to ingest and migrate 50 GB global enterprise data daily into Google BigQuery for making data accessible to stakeholders •Used dbt on BigQuery to model data and maintain tested, reusable views across multiple raw sources (internal global enterprise systems) for project managers for BI tools •Implemented dbt tests, builds, and deployments with GitHub Actions for automated ingestion, testing and debugging for BigQuery, enabling CI/CD and reducing manual errors.

Data Analyst at Bayer, Dec 2022 - Mar 2026 · 3 yrs 4 mos, Bangalore Urban, TimeCard2.0 — Crop Science R&D: Led development of a Python Dash application replacing a legacy reporting system across 62 cost centers and 362 users globally, delivering ~$300K/year in license cost savings. Collaborated with cross-functional stakeholders to gather requirements and rigorously tested for data reliability and performance before rollout. Tools: Python Dash, PostgreSQL, AWS (ECS, Fargate, IAM, CodeBuild) Financial Cost Reconciliation & Discrepancy Analysis: Built a Power BI report that uncovered a ~$1M cost discrepancy across countries and cost centers, tracing it to an incorrect resource conversion metric and driving corrections to budget reporting accuracy. Cleaned and processed cost/project data in Python, sourced from BigQuery pipelines refreshed daily via automated cron jobs. Tools: Power BI, Python, Excel

Data Science Analyst at Bayer, Aug 2021 - Dec 2022 · 1 yr 5 mos, Bangalore Urban, Built an end-to-end data pipeline to process and analyze large-scale protein sequence data, using iFeature for feature extraction and EDA techniques (box plots, histograms, scatter plots, Pareto analysis) to identify key patterns. Developed and evaluated binary classification models (XGBoost, KNN) achieving 91% accuracy on 100K+ sequences stored in AWS EFS/S3, directly supporting high-quality biologics nominations for Insect Control pipeline decision-making. Deployed a cloning algorithm on a serverless AWS orchestration pipeline using Step Functions, Lambda, Docker, and CloudFormation, resulting in a 53% increase in cloning strategy accuracy and a 60% increase in outsourced clones.

Education

Masters in Statistics and Computing, Statistics and Computing, Banaras Hindu University, Banaras