Kartik Hunsigi

Data Engineer Management & Governance Sr Analyst

Accenture

Hyderabad

09.2019 - Current

Hands-on experience in Python.
Good exposure in data handling, data pre-processing, transformation, and sampling techniques.
Skilled in AWS architecture, including SageMaker, AWS Batch, AWS Quicksight, and AWS Step Functions.
Perform code documentation, review, and transitions from R.
Conducted detailed data analysis to uncover trends, patterns, and insights, leading to data-driven decision-making across multiple business units.
Analyzed large datasets using statistical techniques to identify key performance indicators (KPIs) and support strategic planning.
Created interactive dashboards and visual reports in tools like Tableau, Power BI, and AWS QuickSight, enhancing data accessibility for stakeholders.
Designed custom data visualizations that simplified complex data stories, improving communication with non-technical teams.
Developed KPIs for RR25 - Rolls-Royce Spectre in AWS QuickSight, including Charging Location, Displayed SOC Unplugged, Average Charging Power DC, and Seat Occupancy Rate.
Built a Predictive CLV classification model to forecast customer purchase likelihood (buy/no buy) and expected quantity (0, 1, or 2+).
Experience AWS cloud infrastructure, such as AWS Terraform for Infrastructure as Code, and AWS QuickSight for creating visual dashboards.
Deployed code through a CI/CD pipeline with proficiency in GitHub.
Built and deployed Docker images.
Integrated batch jobs with AWS Step Functions.
Decoupled and containerized ML model training pipelines.
Analyzed data through various charts (e.g., pie, bar etc) in AWS QuickSight to derive insights.
Skilled in AWS Athena, AWS Glue, AWS S3, and AWS SageMaker.
Migration of the models from INT environment to PROD environment for deployment via GitHub.
Proficiency in using tools like GitHub, Docker, Ubuntu, VS code, etc.
Experience in working with Sagemaker ecosystem and components like Sagemaker Clarify, Sagemaker CloudFormation templates, Sagemaker SDKs, Feature store, Experiments, E2E deployment, Pipeline creation, Model Registry, ECS, ECR repositories.
Analyzing classification model based on the client's dataset and performing various steps like preprocessing, feature engineering, exploratory data analysis, modeling, and model evaluation.