Jul 2024 – Present · 1 yr 8 mos

Jun 2021 – Jul 2024 · 3 yrs 1 mo

• At Customer Experience Office(CXO), I've fostered strong technical relationships and executed complex requirements across multiple teams. My responsibilities have ranged from high-level architecture and design, API schema designs, to optimizing queries for improved API performance. I've played a key role in maintaining code quality, developing team ownership, and onboarding new team members.
• I've led several projects, including the Sustainability and Full Stack initiatives, the one-click automation for Firmware updates, Software risks, and Cloud Tiering recommendations, and the API migration to Graph. My work has significantly reduced manual time consumption and improved team efficiency.
• In my current role in the team, I'm working on Fusion, a pre-sales tool that translates customer capacity and performance needs into quotable NetApp storage solutions. My primary responsibility is to streamline the core sizing module of Fusion. This involves leveraging mathematical and machine learning techniques to accurately size and match customer requirements with NetApp's storage solutions.

May 2019 – May 2021 · 2 yrs

• Worked on the digital transformation of NetApp's 'Active IQ' Cloud Services Platform : A unified platform for Predictive Analytics, Actionable intelligence based on the telemetry data from the entire portfolio of NetApp products.
• As a part of the initiative to accelerate customer decision making and pro-active avoidance of risks, worked on a Micro Service which identifies the problematic risks and suggests the mitigation action using Ansible Automation.
• This REST API Micro Service is developed using python and AWS Lambda Functions, deployed using AWS gateway and CloudFront by using AWS CloudFormation templates.
• Worked on a POC to understand the impact of risks in customer's environment which involved data extraction, cleanup and developing complex data parsers in Python.
• Worked on a project which predicts the failure of a hardware component in a customer's data center which includes data extraction and modelling using statistical models such as Weibull distribution using Python.
• ML based Rule Platform - A machine learning initiative which can automatically generate new rules based on various parameters extracted from the install base. It identifies various parameters which can result in disruptions. Data extraction was done from around 300,000 systems using Python, ~3TB data is parsed and fed to various classification and clustering models like SVM, Random forests, XGboost, Gradient Boosting, Adaboost and Logic Regression.

May 2018 – Apr 2019 · 11 mos

• Played an important role in the transition of the team from building support tools to deliver unmatched customer experience and value by leveraging power of DevOps, AWS Services, Analytics & Machine Learning and containerization.
• Developed and deployed 4 Micro Services(REST APIs) using Flask framework. The deployment was 100% automated using AWS EC2, Load Balancers, Auto-scaling configurations and containerization techniques. Used Jenkins for Continuous deployments.
• MetroCluster Visualization - MetroCluster is one of the most complex solutions offered by NetApp. This project was aimed at helping customers understand the configurations with pictorial representation. Developed an algorithm in Python to parse the data and generate the exact view of customer's configuration which involved hundreds of different components and fitting them on a computer screen with least overlap and complexity.
• Community Wisdom - A data analytics initiative to compare a storage system with all other systems in the community and detect deviations, popular configurations using entropy. The data extraction and modelling is done using PySpark which extracts data from more than 300,000 systems.
• Casify - A machine learning initiative to find duplicate customer cases and automatically find resolutions to reduce the time and effort to solve a customer cases. The cases are divided into groups and then we use TF-IDF, SGD classifiers, SVM and cosine similarity techniques to find best possible resolution for a new customer case.
• Case Prediction - A machine learning project which correlates customer cases and risks and helps the user in understanding the impacts of having risks in his environment. Used ARM model and PySpark for data extraction and modelling.

Jul 2016 – Apr 2018 · 1 yr 9 mos

• Joining as an NCG, I was provided with an opportunity to work on multiple projects.
• ClusterView - A micro service which enables customers to have a cluster-level view of their configuration. The information included storage, capacity and visualization of the entire configuration. This was developed in Python using Django Framework.
• Data Center Insights - A micro service which enables customers to view his topology beyond the storage system by parsing the information related to the systems connected through various protocols like NFS/CIFS/iSCSi. It involved complex parsing algorithms and extracting large data. This was developed and deployed in python using Django Framework.
• Worked on mulitple POCs which helped the team migrating from a desktop application to web-based microservices. Dockerized the entire POC and deployed on AWS as web service.
• Worked on multi platform support(installers) for the configuration based tools(Windows/Linux/Mac)