Vijay Yadav

• Experienced Data Engineer with strong foundation in Distributed Computing, Data Modeling, Data Quality practice.
• Results driven professional with 7+ years of expertise in Python, NoSQL, SQL, Multi Cloud platforms (AWS, Google Cloud)
• Proficient in Real-time streaming applications, NoSQL Implementations, Data Warehousing, and Agile Practices.
• Adept at Data pipeline optimizing techniques, communicating data-driven insights and drive business success initiatives.
• Strong verbal and written communication skills, enabling effective collaboration with cross-functional teams.

Senior Data Engineer, Allianz Life April 2018 – Dec 2021

Tech Stack: Python, PySpark, Scikit-learn, SQL, Mage, AWS Cloud

• Crafted a scalable Recommendation System data pipeline using Python Scripting, AWS components (S3, EMR, Glue,

Redshift), and advanced data visualization tools like Tableau and PowerBI for insightful data analysis and recommendations.

• Designed claims automation system to seamlessly handle large volumes of daily and weekly data, supporting multiple teams like fraud preventions, underwriters, marketing, and agency team enabling them with custom DataMart.
• Managed & orchestrated data pipelines for real time marketing campaign, utilizing Apache Airflow, Kafka, and SQL procedures.
• Developed a fraud detection model using Random Forest for the Claims team, saving the company potential financial losses by identifying and preventing fraudulent claims worth $1.5 million in a single quarter.
• Trained 36 associates on Data Engineering core concepts with hands-on programming using Python, SQL, and Airflow to provide technical guidance to junior team members, fostering their professional growth & ensuring high-quality deliverables.

Machine Learning Engineer, Tata Consultancy Services July 2015 – March 2019

Tech Stack: Python, Airflow, Splunk, Ansible, Linux

• Developed robust automation scripts for model deployment using Docker & Kubernetes, monitoring and maintenance, reducing deployment time by 70% and ensuring continuous model performance tracking.
• Conducted POC’s for multiple client site, improving performance tuning and optimization of existing machine learning models,

achieving a 5% improvement in accuracy, and reducing resource consumption.

• Implemented named entity recognition (NER) models using spaCy and BiLSTM-CRF (Bidirectional LSTM with C

Masters in Data Analytics - Clark university