Swapnil Chandrakant Zambare

Python ML/AI Engineer – Virtusa Technology - https://www.virtusa.com/)

Objective Experience

To employ myself in a progressive organization that Technology Specialization :

provides scope to update my practical knowledge and skills
Python Data Science | Big Data | Machine Learning | Django REST | Mongo DB |PySpark |
in accordance with the latest trends and be part of the
ETL / Data warehousing | Business Intelligence | Unix
team that dynamically works towards growth of the
organization. Associated Technology : AWS, Docker, Power BI, ETL(Data Migration), Linux,
Looking for a ML Engineer Job where I can utilize my
Programming skills to Develop Data Science /Machine
Learning / Web Application (Django Rest Framework Currently working with client Central Bank of India as ML Engineer for ‘Integrated Loan
components/System .To achieve a challenging position as Management/Cibil ML. Pipeline’.
a Python Programmer in a result-oriented company,
where acquired skills and education will be utilized Work Experience with clients : Central Bank of India| SecurePay, Australia | Freenet
towards continuous growth and advancement. AG,Germany |
System/Vertical Worked with : Banking | Supplychain analytics | Telecom OSS | Payment
Gateway

Contact
Technical Qualification Headlines :
Phone no.:- +91- 8657387144
Email: [email protected]
Currently working as a ’Python-Data Scientist’ for ‘Integrated Loan Management/Cibil ML.
Pipeline’ with client Central Bank of India. Strong work experience with Technology ETL /
Big Data / Business Intelligence / Analytical Language using PySpark. Web Framework
involvement: Django REST.
Education
Experience with Core Data Science/ML Libraries /Packages :
 B.E (Instrumentation)
 University: North Maharashtra University, PySpark | Pandas | Numpy | Seaborn | Matplotlib |Scikit Learn | Keras | Tensorflow |
Jalgaon Scipy | Statsmodels | Plotly
 College : Government College of Engineering,
Experience with Core Django REST Libraries /Packages:
Jalgaon
Django-rest-framework | Django-cors-headers | Django-debug-toolbar | Django-
extensions | Sentry-sdk | Django-allauth | Django-filter | Django-import-export |
Personal Info
Major Tools , Associated Technologies & Environment
 Father name : Chandrakant Onkar
Zambare  Unstructured Database Used – Mongo DB
 Mother’s Name: Madhuri  UI Application Programming Language - HTML, CSS, JavaScript, JQuery and
 Permanent address: 184, Zambare Wada, Bootstrap.
Khiroda,Tal Raver, Dist Jalgaon ,  Web Scraping Library : Beautiful Soup 4
Maharashtra 425504  Web Framework involvement : Django REST
 Temporary address: Flat no 203,Ketaki  BI Tool used - Tableau
Coperative Housing Society, near  Parsing XML - xml Schema
Lokmanya Nagar Post Office, Lokmanya
Nagar, Pune 411030
Experience with Machine Learning Algorithm
 Date of Birth: 25-02-1994
 Marital status- Unmarried Linear Regression | Logistic Regression | KNN |K-Means |Naïve Bayes |Mean, Median,
 Gender: Male Mode |Decision Tree |Random Forest
 Language: English, Hindi, Marathi Support Vector Machine |Principal Component Analysis |NLP |XG Boost
 Passport: Yes
Process worked with: DevOps + Agile + V- Model

HOBBIES Software Programming Language Experience:

 Reading
 Research
 Cycling
 Music
Business Implementation Programming Experience:

Machine learning – Python | ETL – Python | Business Intelligence

Strong Experience Areas

Python | SQL |Machine Learning Algorithm | Django Web service-REST

Key Skills

 Frameworks: Django, CSS , Bootstrap.

 Web Technologies: HTML, CSS, Java Script, JQuery, J SON, XML.
 Programming Languages: Python, HTML, CSS, SQL.
 Version Control: Git, GitHub.
 Cloud Computing: AWS EC2, S3, Glue,Redshift,RDS, ECS, ECR, lambda ,step machine
 Analytic Tools: PySpark,Pandas
 Application servers: Apache Tomcat,Nginix, JBoss,WebLogic,WebSphere.
 Databases: Oracle 10g, My SQL, MongoDB.
 IDEs/ Development Tools: PyCharm , Anaconda – Jupyter Nb , Atom, Spyder , Microsoft Visual Studio.
 Operating Systems: Windows, Red hat Linux .
 Protocols: TCP/IP, HTTP/HTTPS, SOAP.
 Deployment Tools: Heroku, Jenkins.
 Issue Trackers: JIRA tools
 Web Service : DRF (Django Rest Framework)

Working Zone Organization

Worked as a Python ML/AI Engineer with Virtusa Technology, Pune (https://www.virtusa.com/) Pune since May 2021 -
Present.

Achievements
 Received “Star Performer Award” from Virtusa for good performance.
 Received appreciation for E2E Delivery from client SecurePay, Australia , Australia

Projects

Project Sequence 1

Project Name : Industrial Ethernet Switch - SCALANCE X -Siemens

Client : Freenet AG,Germany
Vertical : Telecom OSS Provisioning and Activation –Inventory Management
Technology & Tool : Python , Django REST , Oracle ,GIT , Rest – Web Service ,Pandas, ETL, Statistical Analysis.
Role : Python Developer

Detail Project Overview and Workflow:

Powerful industrial communication networks are the foundation for digitalization. Within these networks, data must be
systematically and reliably distributed across all levels. Industrial Ethernet switches are perfect for the job. With SCALANCE
X, Siemens offers several product lines with different functional scopes depending on the specific networking task – the right
switch for every application. The segmenting of networks by means of virtual local area networks (VLANs) significantly boosts
cybersecurity. VLANs act as broadcast blockers and only permit data traffic between defined participants, meaning that
potential cyber-attacks can affect only a small number of participants, if any.
Project Sequence 2

Project Name : Stream processing and Supply chain Execution

Vertical : Supply Chain Analytics
Client : Freenet AG, Germany
Technology & Tool : Python, PySpark, Spark SQL, Plotly, Dash, Post Man ,Microsoft Azure, Docker, ETL, ML ,Statistical
Analysis
Roles : Python Developer /Data Scientist

Detail Project Overview and Workflow:

Inventory management is extremely crucial for supply chain management as it allows enterprises to deal and adjust for any
unexpected shortages. No supply chain firm would want to halt their company’s production while they launch a hunt to find
another supplier. Similarly, they wouldn’t want to overstock as that starts affecting the profits.
Inventory management in supply chain is largely about striking a balance between timing the purchase orders to keep the
operations going smoothly while not overstocking the items they won’t need or use..Integrating machine learning in supply
chain management can help automate a number of mundane tasks and allow the enterprises to focus on more strategic and
impactful business activities.
Using this intelligent machine learning software, supply chain managers can optimize inventory and find most suited suppliers
to keep their business running efficiently. An increasing number of businesses today are showing interest in the applications
of machine learning, from its varied advantages to fully leveraging the huge amounts of data collected by warehousing,
transportation systems, and industrial logistics.

Project Sequence 3

Project Name : Log Automation [ LogAut ]

Vertical : Payments Analytics
Client : SecurePay,Australia
Technology & Tool: Python, PySpark, Spark SQL, Plotly, Dash, Postman, Docker, ETL, Machine Learning,
Statistical Analysis

Roles : Python Data Scientist

Detail Project Overview and Workflow:

Take advantage of on-demand payment analytics and business intelligence streaming, combined with leading-edge AI and
machine learning, to make timely data-driven business decisions.

Access rich records of every customer interaction to spot top customers, identify customer acquisition opportunities, and
analyze card usage across all payment channels.

Reduce the expensive, resource-intensive cycles it takes to gather payment transaction data; and build reports, forecasting
models, and predictive algorithms for payment analytics. Centrally collect real-time transaction data across all card and
payment channels, without complicated deployment. Easily generate reports on customer usage, card profitability, and
channel performance, and see them in dynamic dashboards. Quickly recognize patterns and predictions related to risk scores,
queue lengths, cash flow forecasting, revenue, card usage, and customer buying behaviors. Forward data to analytics
applications or data lakes of choice, including Tableau and Microsoft Power BI.

Project Sequence 4

Project Name : Integrated Loan Management/Cibil ML. Pipeline

Vertical : Banking
Client : Central Bank of India
Technology & Tool: Amazon AWS, Python, Machine Learning
Roles : Python Data Scientist - ML Engineer

Detail Project Overview and Workflow:

The project pipeline involves collecting loan and credit data from multiple sources, including CIBIL, integrating them into a
unified database, developing machine learning models like logistic regression and random forest for tasks like credit risk
assessment, training these models on the collected data, and finally deploying the best-performing model into a production
environment integrated with the loan management system.

Task Handled:

 Integrate the collected data into a unified database/data warehouse.

 Built Factor Analysis and Cluster Analysis models using Python SciPy to classify customers into different target
groups.
 Data Wrangling, preprocessing, and visualization.
 Feature engineering and feature selection are explored with theobjective of achieving superior predictive
performance.
 Use predictive model building like Logistic Regression, Random Forest, Decision Tree, SVM, XGBoost, GBC to
increase and optimize customer experiences, revenue generation, and other business outcomes.
 Evaluate the trained models using appropriate evaluation metrics such as accuracy, precision, recall, F1-score etc.
 Take part in deployemnt of best-performing model into production environment.
 Document the entire pipeline including data sources, preprocessing steps, model development, evaluation metrics,
and deployment procedures.

Declaration:-
I hereby declare that the above-mentioned information is correct to the best of my knowledge.

Date: -
Place: - Pune.

Regards

Swapnil Chandrakant Zambare