CAREER SUMMARY:

Data Engineering, Machine Learning, Business Intelligence and Artificial Intelligence Solution Architect with 16 years of experience. Vast hands - on experience with Data profiling, Data Integration, Data Science, Data visualization and cloud data migration. Worked with top IT companies in customer facing role and participated in business proposal development along with sales team as lead technical consultant and architect.

TECHNICAL SKILLS:

Machine Learning: Supervised, Unsupervised, Ensemble, Decision Tree etc.

Deep Learning: Artificial Neural Network, Convolutional Neural Network, Tensorflow, Keras, Natural Language Processing

Visualization: Power BI, Tableau

Cloud Platform: Azure, Google cloud platform, AWS

ETL: Informatica Power Center, Informatica Admin, Informatica Cloud, SSIS

Reports: Business Objects, SSRS

Data Base: Oracle, DB2, ASDW, SQL Server

Data Modeling: Data profiling, Data analysis, and modeling experience

OS: Windows, UNIX, Linux

PROFESSIONAL EXPERIENCE:

Confidential

AI/ML Architect

Responsibilities:

• Work on with Azure Data Lake for storing machine logs and performed EDA of different data fields from log and their relation to failure
• Build right ML model in Python and Azure for forecasting any failure and preventive suggestions through model prediction. Used Keras deep learning model as well as random forest from ensemble bagging family.
• Also collected different system issue related ticket history from pharmacy, used different text preprocessing techniques, natural language processing techniques like count vectorizer and TfIdf vectorizer to feed into model. Predicted the right ticket category and generated text for new automated ticket creation.
• Used different text preprocessing techniques using libraries and components like BeautifulSoup, Spacy, Spacy tokenizer, Stop Words, Contractions, and regular expression.
• Providing the statistics in Power BI executive dashboard for senior leadership in IT and Business side for better decision making.

Confidential

AI/ML Architect

Responsibilities:

• Work on PostgreSQL on GCP for teams’ ticket and slack communication related data and built dashboard on top of it using Power BI foe different ticket statistics.
• Get the right scrum related ticketing data from JIRA and other ticketing systems then model and store the data in flexible and user-friendly structures
• Build different performance analytical dashboards with predictive and prescriptive model in Power BI
• Build right ML model in Python and Azure for forecasting teams’ behavior and predicting the return on investment of different initiative. Used linear regression and gradient boost.
• Provide different teams comparison with each other as well as vs entire area, team’s ranking and all different sort of base data summary and statistics
• Finding investments and different business solutions, initiatives, Products and Workstreams and the return of investment using Power BI Dashboard.
• Used Convolutional Neural Network (CNN) to identify and classify pharmacy scanned images to help scrum teams with image classification.
• Used different filters and gaussian blurring techniques for better preprocessing of images.

Confidential

ML & BI Engineer

Responsibilities:

• Working with business to identify right customer data
• Exploratory data analysis and identifying the different customer data relation, skew, Kurt, outlier and visualize data distribution
• Use different statistical analysis of hypothesis tests like Anova and Chi Square to identify and analyze customer data better
• Building clusters of customer segments. Used ML models K-Means as well as Agglomerative / hierarchical clustering
• Used logistic regression and random forest for customer classification to identify potential regular customers
• Feed data to database and build business decision making dashboards with predictive and prescriptive model in Power BI

Confidential

ML / BI Engineer

Responsibilities:

• Analyzed fuel IOT gauge data, temperature, evaporation rate, distance, route location and other features to build a Keras model to predict a fuel theft.
• Used different Exploratory data analysis (EDA) techniques and data preprocessing steps for better understanding of the data.
• Confidential worked with business people directly to identify this high priority issue and predict and prevent that.
• Integrated merchandise sales with gas sales to relate the data and perform more accurate market basket analysis
• Gathered historical events data past sales data and analyzed correlations for fast moving items sale
• Built K nearest neighbor and random forest models to predict required inventory based on local event.
• Worked on Power BI Dashboard to present data to business for better and easy, interactive understanding.

Confidential

BI Data Architect

Responsibilities:

• Evaluating different cloud vendors and propose the right cost-effective solution to the customer and defining the road map for Data and BI environment.
• Defining and solutioning the architecture to best achievable performance and need on Azure.
• Performed Data analysis, Data profiling and Data modeling exercise for right performance need
• Built ETL mappings in Informatica using different components like Look up, joiner, update strategy, filter, router etc.
• Created workflow and session, implementing pushdown optimization and partitioning.
• Worked on Informatica Data Quality in integration with address doctor. Perform Column, Rule, Multi object, Comparative and Mid-Stream Profiling. Manage Tables. Develop standardization, cleansing and parsing Mappings and mapplets. Identify duplicate records using Classic Data Matching.
• Worked on Informatica administration, capacity planning, configuring repository services and integration services, configuration and management of user/group/role, LDAP authentication, configuration of nodes and grids along with high availability setup, repository service backup.
• Worked on Power BI Dashboard to prepare scorecard, sales performance, analytical reports.
• Worked on Job automation, Automated monitoring alert, automated post load validation and alert mechanism.
• Reduced monitoring effort by 90% and Reduced ticket count by 40%

Confidential

BI Lead

Responsibilities:

• Working on Informatica administration including capacity planning and installation and upgrade
• Configured repository services and integration services, configuration and management of user/group/role, LDAP authentication, configuration of nodes and grids along with high availability setup, repository service backup.
• Enhancing the ETL architecture, create mappings using Informatica Power Center and load the data into Data Warehouse
• Used different ETL component like lookup, filter, joiner, router, update strategy etc. Created session and workflow using pushdown optimization and partitioning.
• Create Informatica Data Quality mappings to do data validation and Data cleansing exercise. Perform Column, Rule, Multi object, Comparative and Mid-Stream Profiling. Manage Tables. Develop standardization, cleansing and parsing Mappings and mapplets. Identify duplicate records using Classic Data Matching.
• Designing universes and building standard reports in Business Objects for sales performance
• Creating interactive visualization using Tableau on score card, field people performance, Write Off reporting, cost optimization etc.
• Ensuring a smooth transition of the applications to production and Stabilizing the application support
• Reverse engineering the code and extract business logic for the platform and prepare documentation for new platform design
• Understanding business pain points and considering those as input for new platform architecture document

Confidential

ETL Lead

Responsibilities:

• Ensuring the smooth support of production environment including daily batch job handling providing on time report to stake holders
• Designing Informatica mapping for HR/ Payroll data flow using different ETL component like lookup, filter, joiner, router, update strategy etc. Created session and workflow using pushdown optimization and partitioning.
• Working on Informatica administration including daily back up of Informatica repository, performing weekly maintenance, configuration, and management of user/group/role.
• Build reports on business objects for sales, orders, supply chain as per business requirement.
• Build UNIX scripts and wrapper scripts using PMCmd command to automate Informatica workflow triggered via AutoSys.
• Used Informatica, UNIX, Oracle, Business Objects, performed reverse engineering exercise from WebMethods system to extract the logics and implement that in Informatica mappings.

Confidential

Sr. ETL Developer

Responsibilities:

• Building the ETL architecture, create mappings using Informatica Power Center and load the data into Data Warehouse
• Used different ETL component like lookup, filter, joiner, router, update strategy etc. Created session and workflow using pushdown optimization and partitioning.
• Build reports as per business requirement
• Build UNIX scripts and wrapper scripts using PMCmd command to automate Informatica workflow triggered via Control M.
• Ensuring a smooth transition of the applications to production and Stabilizing the application support
• Worked on Job automation, Automated monitoring alert, automated post load validation and alert mechanism.
• Defined different business KPI and built proper logic for that and provided relevant data to business.
• Working on Informatica administration including daily back up of Informatica repository, performing weekly maintenance, configuration and management of user/group/role.

Confidential

ETL Developer

Responsibilities:

• Functional spec understanding and requirement gathering.
• Designing ETL mapping as per functional requirement.
• Develop test and deploy mappings.
• Execute the mappings in production and create data extraction files. Load the files to SAP via LSMW program.
• Build UNIX scripts and wrapper scripts using PMCmd command to automate Informatica workflow.
• Used different ETL component like lookup, filter, joiner, router, update strategy etc.
• Created session and workflow.
• Used SQL Server 2000 and DTS packages to standardize data from different system to make it consumable through the reusable Informatica mappings for different geographical markets.
• Worked on SAP data loading exercise using LSMW programs.
• Loaded data for SAP tables of different objects like Material master, Customer Master, and different transaction tables.