NVK Anirudh

Master of Science

Applied Data Analytics

Jan 2023

Boston University, Boston MA

Courses: Data Science with Python, Machine Learning, Advanced Big Data Analytics, Data Analysis and Visualization with R

Teaching Assistant for the Data Science with Python course under Prof. Eugene Pinsky

Bachelor of Technology

Computer Science

Apr 2019

GITAM University, Visakhapatnam, India

Languages: SQL (Advanced), SparkSQL, Python (Proficient), R

Data Engineering: ETL/ELT, Data Pipeline Development, Data Modeling, Data Warehousing, Apache Airflow, Apache Kafka

Cloud & Big Data: AWS (S3, EC2, ECR, CodePipeline), Azure Databricks, Snowflake, Apache Spark

Data Visualization: Tableau, Power BI

Databases: MySQL, PostgreSQL, SQL Server, NoSQL (MongoDB), Vector Stores

ML Frameworks: TensorFlow, PyTorch, Scikit-learn, Keras, MLFlow

Data Analyst

Feb 2023 - Jan 2024

ATC, Remote, USA

• Designed and implemented ETL processes, transitioning from Excel to RDBMS, reducing data access time by 40% and improving reporting accuracy.
• Streamlined data processing workflows with Apache Airflow for ETL, reducing SQL Server data loading times by 40% and enhanced shell scripts to ensure seamless data loading, boosting system efficiency and responsiveness.
• Implemented Kafka for real-time data streaming, increasing SQL Server ingestion speed by 30% and reducing latency for real-time updates by 20%.
• Developed a cloud-based data warehouse solution using Snowflake, enabling the extraction of valuable insights and improving strategic planning.
• Optimized SQL Server queries, resulting in 30% faster performance and enhanced decision-making capabilities.
• Conducted in-depth data analysis using SnowSQL, producing reports that directly informed strategic decisions.
• Improved data management processes, enhancing data integrity and reducing errors by 25%.

Machine Learning Technical Engineer

Sept 2021 - Dec 2021

BU Spark, Boston, MA

• Integrated CRAFT object detector and Tesseract OCR using TensorFlow, boosting text recognition efficiency by 30% and reducing manual data entry time.
• Implemented name extraction system for Herbarium specimens, cutting identification time by 40% and increasing processing throughput by 50%.
• Mentored 20 students of Data Science with Python course, leading 4 projects with a 90% completion rate and enhancing student understanding of data science projects.

Data Scientist

Feb 2019 - Aug 2020

Intain Technologies, Chennai, India

• Developed and deployed a Mask-RCNN model for document field extraction with 95% precision, reducing data processing time by 70% and enhancing data accuracy.
• Automated field extraction with Docker and Flask, cutting manual data entry by 80%, saving 200+ work hours monthly, and improving workflow efficiency.
• Enhanced field extraction accuracy to 97% with Mask-RCNN, surpassing RegEx by 7%, reducing errors by 20%, and increasing data reliability.
• Managed version control with GitHub and communicated technical insights to stakeholders, leading to better project alignment and informed decision-making.