Data Scientist

Data Scientist with expertise in machine learning, statistical analysis, and big data technologies. Proficient in developing data-driven solutions through predictive maintenance, time series forecasting, and managing data pipelines for real-time insights. Skilled in developing data-driven solutions and delivering insights through Power BI and Grafana. Passionate about driving impact through data and continuously expanding technical expertise.

Experience

Data Scientist @ Cloudfm (January 2022 - Present)

Utilized PostgreSQL and InfluxDB for managing and analyzing time series data to derive insights.
Worked extensively with Kafka and Azure tools like Databricks and Synapse for data management and analysis.
Developed comprehensive energy usage reports that reduced client energy consumption by 12.5%.
Created an algorithm that assesses asset health using parameters like power factor (PF) and total harmonic distortion (THD) with harmonics.
Worked with Power BI and Grafana for data visualization and reporting.
Developed machine learning models for time series forecasting, and predictive, preventive, and conditional maintenance to improve asset management.
Built and managed data pipelines to generate insights and communicate findings.
Facilitated knowledge transfer between business and clients by creating comprehensive reports that led to a reduction in energy consumption.
Created internal projects to alert the business of any data loss from sensor endpoints.
Participated in the production team for developing a model to detect changes in fan speed status and its different states.

Data Analyst @ Reliance Jio Platform (December 2020 - August 2021)

Delivered business outputs using Scala on the Spark framework.
Derived data from source points using Hive, SAP Tools like SAP Hana and PL/SQL.
Provided end-to-end solutions for the data needs of business using Kafka, API, and JSON.
Collaborated with peers to develop solutions using Git.
Delivered streaming data to businesses using Apache Flink.
Used Airflow to deploy DAGs using Python.
Managed and assessed data of everyday business queries using Ambari.
Trained juniors to use tools and languages such as IntelliJ, Git, Shell, and Scala.

Android Developer Intern @ VEM Tooling (June 2019 - April 2020)

Built an Android application of size less than 1.5 MB.
Deployed the application on Google Playstore.
Developed a machine learning model for the detection of butterfly species (accuracy >70%).
Used TensorFlow and CNN algorithms to build the model.
Formed Structured Dataset and curated the set of Butterfly species.
Created a game that rewards users with Coupons in the form of a QR code.
Set up an Admin application to manage user data and scan QR codes.

Education

M.S., Data Science, Dept. of Mathematics University of Essex Distinction (2023)
B.E., Information Technology Savitribai Phule Pune University (2021)

Certifications

The Butterfly Garden App (Certified By the Government of India)
SQL for Data Science Coursera (2021)
Bits and Bytes of Computer Networking Coursera (2020)
How Google Does Machine Learning Coursera (2020)
Google Cloud Fundamentals: Core Infrastructure Coursera (2019)

Skills

Frameworks: Spark, Kafka, Airflow
Machine Learning & Data Science: Predictive maintenance, Neural networks, LLMs, Statistical analysis, Time series forecasting
Data Tools: SAP Hana, PostgreSQL, InfluxDB, Databricks, PowerBI, Grafana
Languages: JavaScript, Scala, Python, R
Cloud Platforms: Azure (Data Studio, Synapse, DevOps), Google Cloud
Leadership & Project Management: Agile, Scrum, Stakeholder management
Visualization & Reporting: Power BI, Grafana, Miro Board
Soft Skills: Leadership, Critical Thinking, Communication, Teamwork

Passion Projects

In my spare time, I enjoy working on full-stack web development projects using frameworks such as React, Next.js, Astro, and Three.js. I’m also passionate about creating Discord bots and exploring the world of web3 and Artificial Intelligence. These projects allow me to explore creative solutions, sharpen my development skills, and stay up to date with emerging technologies.