Sohail Ali Shaik
Data Scientist
Delhi
Summary
Solution-oriented data scientist with 3+ years of experience in building data intensive applications, overcoming complex architectural and scalability issues. Proficient in predictive modelling, data processing and data mining algorithms, as well as scripting languages. Worked on developing, testing and deploying diverse services to translate business requirements into timely deliverables.
Overview
4
4
years of professional experience
5
5
years of post-secondary education
Work History
Machine Learning Engineer
Mad Street Den
Chennai
09.2020 - Current
- Working with Tata Digital for Tata Neu, where we handle the search & personalization.
- Developed, monitored and improved performance of the popularity based ML model to predict trending.
- Built recommendation system using collaborative filtering to bolster the user personalization.
- Adept at Python and used it to build microservices for handling assembly of results adding different layers of personalization.
- Designed the architecture of many widgets and microservices and also effectively worked on cost and time optimization for application layer and services like redis.
- Built pipelines using Pyspark in Azure Databricks to process and handle huge data loads - covering threading, query database and search platform like cosmos, DWH and solr.
Data Scientist Intern
Moengage Inc.
Bengaluru
11.2019 - 05.2020
- Worked on the project “Improving Sherpa – DMV Testing”, which uses Multi Armed bandits theory.
- Focused on MAB algorithms like Epsilon, Greedy – epsilon, Thompson sampling and UCB.
- The process involved extraction of data from multiple databases using BigQuery and Athena, data Preparation and Analysis using python.
- Analyzed the existing Sherpa AI Engine and improved the overall system efficiency by 5 % to provide a 15 % boost in the CTR for clients.
Data Scientist (Practicum)
CCC Information Services Inc.
Chicago
01.2019 - 05.2019
- Worked on "Anomaly Detection in AWS Cloud Log Trails", where we tracked 40 GB of CCCIS Employee data regarding the usage of AWS.
- Implemented algorithms Random Cut Forest, Isolation Forest and visualized the generated results using bokeh and seaborn.
Education
Master of Science - Data Science
Illinois Institute of Technology
Chicago, USA 08.2017 - 05.2019
Bachelor of Technology - Computer Science
Sreenidhi Institute of Science And Technology
Hyderabad, India 08.2013 - 05.2017
Skills
Machine Learning
Microsoft Azure
Databricks
Python
SQL
Jenkins
Kibana
Computer Vision
GIT
Tenserflow
PyTorch
Accomplishments
- Published Research papers in International Journals on Applications of Hadoop Technologies On Text Processing in IJSER and Predictive Analytics: Cognitive Analysis in OJCST
- Coursera certified R programmer
- Worked as Resource Person and conducted workshop for 90 members on IOT and Hadoop - Big data Technologies and successfully received an accomplishment.
Timeline
Machine Learning Engineer
Mad Street Den
09.2020 - Current
Data Scientist Intern
Moengage Inc.
11.2019 - 05.2020
Data Scientist (Practicum)
CCC Information Services Inc.
01.2019 - 05.2019
Master of Science - Data Science
Illinois Institute of Technology
08.2017 - 05.2019
Bachelor of Technology - Computer Science
Sreenidhi Institute of Science And Technology
08.2013 - 05.2017