Work Experience
Data and Applied Scientist II - Microsoft
Feb 2022 - Current
I am currently working in the cloud supply chain team as a machine learning engineer with focus on building large-scale data processing systems.
Technical Instructor - Interview Kickstart
Nov 2023 - Current
I am currently working as a technical instructor at Interview Kickstart. I teach industry professionals topics including
- Python
- Machine learning
- Deep learning
- Data analytics
Data Scientist - Tech9
Dec 2019 - Feb 2022
Engineering
- Developed a serverless GraphQL Backend on Google Cloud
- Developed ETL pipelines on apache airflow (Cloud Composer with GKE)
- Designed the database schema for the application from ground up.
- Developed CI/CD pipelines for faster and reliable code delivery
- Developed loosely coupled, event-based, cloud native micro-services
Machine learning
- Developed a classification model to categorise financial transaction and predict transaction categories
- Developed a classification model to find website that solely exist to boost the ranking of target websites in search engines
Programmer Analyst - Octathorpe
Dec 2017 - Nov 2019
- Developed tree-based machine learning models for user segmentation and classification that resulted in a 30% increase in the revenue across projects
- Developed machine learning models for revenue forecasting and risk assessment
- Implemented new frameworks like firebase for better data collection, spark for processing bigger datasets
- Developed play store scrapers to find the best keywords for data-driven app store optimization
- Conducted statistical data analysis on user data to improve key business metrics like day 1 retention, from 12% to 25%
- Created data visualization dashboards and decreased the product turnaround time by 40%
- Improved user engagement by carrying out data-driven A/B experiments
- Developed ETL pipelines for processing the clicks and interactions data of users
- Optimized queries to reduce the costs incurred in querying data from bigquery
Technical Skills
- Languages: Python, R, C++, Java, SQL
- Frameworks: Pytorch, PySpark, Keras, Fastai, Pandas, Numpy, Sklearn, Plotly, Matplotlib, SparkML, nltk, SpaCy
- Technologies: Bash, Git, UNIX, Google Cloud, AWS, IBM Cloud
- Databases: MySQL, SQLite, MongoDB, HDFS, Amazon Data lake, BigQuery, IBM object storage
Certifications
All certifications