Summary
Overview
Work History
Education
Skills
Websites
Certification
Projects
Timeline
Generic

Akanksha Purwar

Bengaluru

Summary

As a Data Engineer with nearly 2 years of experience at a product-based startup and an internship at Intel, Bangalore, I specialize in data pipeline development, automation, and analysis using Python and SQL. I leverage AWS for cloud infrastructure, Airflow for orchestration, and Docker for consistent deployments. With expertise in machine learning and NLP I’ve driven product insights through sentiment analysis, buzzword detection, and word counting. As the sole point of contact for Sales and ML-related tasks, I bridge technical teams and stakeholders, ensuring smooth and impactful project execution.

Overview

1
1
year of professional experience
1
1
Certification

Work History

Data Engineer

Anchanto Services | Digital Shelf
Pune
12.2023 - Current
  • Built and automated scalable data pipelines for Digital Shelf using Python, SQL, AWS, Airflow, and Docker.
  • Owned data scraping and ETL processes to centralize e-commerce metrics like pricing, promotions, and availability.
  • Applied NLP and ML to extract insights on content quality, share of search, and performance trends.
  • Delivered actionable, data-driven insights to support marketplace optimization strategies.
  • Acted as the single point of contact for sales and ML features, aligning tech solutions with business needs.

Internship

Intel
  • Created Deep Learning Models for various Combinational and Sequential designs that includes creating data from RTL designs and Preprocessing of data for Neural Networks and feeding data to models for output prediction
  • Helped automation team automate manual processes using perl and shell scripting.

Education

B.Tech/B.E. -

Dr APJ Abdul Kalam Technical University
08-2023

12th -

S.R. Public School
08-2019

10th -

S.R. Public School
08-2017

Skills

  • Programming Languages: Python, C/C
  • Database: SQL, PostgreSQL
  • Cloud: AWS
  • Containerization & Deployment: Docker
  • Workflow Orchestration and Pipelines: Airflow
  • Version Control: Git and Github
  • Data Engineering: Data Scraping, ETL, Data Pipelines
  • Machine Learning: NLP, Feature Extraction, Model development
  • ML and Python Libraries: Pandas, Numpy, Spacy, Scikit-learn, plotly, matplotlib, Tensorflow, NLTK, BeautifulSoup
  • Development Tools: VS code
  • OS: Windows, Linux

Certification

  • Machine Learning by Andrew Ng
  • Python
  • SQL Advanced

Projects

Melanoma Skin Cancer Detection | College

Analyzed pre-trained models (e.g. MobileNet and VGG-16) with and without augmentation, address issues in cancer detection; developed MelaNet, a deep learning model for melanoma skin cancer detection, mitigating overfitting and deploying it on a UI 

Digital Shelf | Anchanto

The process collects data, transforms it via ETL pipelines, and ingests it into a database. This data powers the Digital Shelf UI, providing insights on pricing, promotions, content quality,  and product availability. Machine learning and NLP enhances these insights for data-driven analysis, enabling customers to make informed decisions and optimize strategies.

Timeline

Data Engineer

Anchanto Services | Digital Shelf
12.2023 - Current

Internship

Intel

B.Tech/B.E. -

Dr APJ Abdul Kalam Technical University

12th -

S.R. Public School

10th -

S.R. Public School
Akanksha Purwar