Sherwin Varghese

Sherwin Varghese

About Me

Hello!

I am Sherwin Varghese.

Full Stack Web application developer at SAP SE with over seven years of experience in Cloud application development.

Computer science graduate holding Masters in Software Systems with Data Analytics specialization. Handled projects used by over 150M users with 1.2B transactions per day.

My research interests include Machine Learning, robotics and IoT.

  • Interests: AI, ML, IOT, Robotics
  • Coding Languages: Java, JS, Python
  • Current Employer: SAP SE
  • Residence: India
Expertise
Web Application Development

Developing web applications using Angular for the UI and Java for the backend.

Cloud Application Development

Experienced in developing Paas, SaaS cloud based applications, including developing and deploying in Google Cloud Platform.

IOT and Embedded Systems

Made Internet of Things (IOT) projects using Raspberry Pi, Arduino and sensors.

Machine Learning

Worked on Recommender Systems, exploratory data analysis and data cleaning.

Career Objective
To be the best in class in computer science research and work with dedication and enthusiasm for the betterment of the organization and society.
Fun Facts
Known Languages: English, Hindi and Malayalam
Familiar Operating Systems: Debian, Mac OSX, Windows
Databases used: SQL, MySQL, MongoDB, PostgreSQL
Free and Open Source Software enthusiast
Resume
Exprience
October 2021 - Present
Machine Learning Developer
SAP New Ventures & Innovations - SAP SE

Designed the Knowledge Graph Ontology for a system that recommends ideal engineers for solving customer tickets.
Devised benchmarks on traditional ML algorithms (TF-IDF, Random Forest), achieved higher top-K hit rates for top 50, 100, and 200 engineers with embeddings.

June 2021 - Present
Senior Full Stack Developer
SAP Customer Experience - SAP SE

Lead developer of the SAP Customer Data Cloud, developed UIs and integration APIs for SAP Commerce Cloud V2.

November 2019 - June 2021
Full Stack Developer
SAP Customer Experience - SAP SE

Pioneered User Interfaces using Angular for CX Integration Automation

June 2019 - November 2019
API Developer
SAP Customer Experience - SAP SE

Introduced over 15 GraphQL APIs in Java and Golang for CX Integration Automation that reduced the initial configuration effort by 33%.

June 2018 - May 2019
Backend Developer
SAP SuccessFactors - SAP SE

Implemented the suite wide initiative of phasing out Hibernate entities, changing 200+ files, increasing DB throughput by 7% & reducing additional costs by 10%.

September 2015 - May 2018
Frontend Developer
SAP SuccessFactors - SAP SE

Ensured accessibility, RTL layout standards of the product, doubling as a security expert in resolving over 75 Cross-site Scripting issues.

Education
2017 - 2019
Birla Institute of Technology and Science (BITS), Pilani
BITS Pilani

Master of Technology (M.Tech) in Software Systems with specialization in Data Analytics - Work Integrated Learning Programme (WILP)

2011 - 2015
Mahatma Gandhi University, Kottayam
Federal Institute of Science and Technology (FISAT)

Bachelor of Technology (B.Tech) in Computer Science & Engineering

Skills
Frameworks and tools
Spring
Angular Framework
PyTorch
TensorFlow
Software Design
Knowledge
  • Full Stack Web development
  • Cloud Application Development
  • Internet of Things Prototyping
  • Robotics
  • Machine Learning
  • UX Design
Coding
85%
Java
80%
JavaScript
75%
Python
60%
Golang
Languages
English
Malayalam
Hindi
Research
Publications
Relevance of Bots in Software & their impacts on Software Security
World Congress on Engineering (WCE2021)
Elson Kurian*, Sherwin Varghese*, Stefano Fiorini
Robots or bots are an integral part of the computer software. Bots are preferred over humans in many services due to its perceivable passionate personality. This paper discusses about the different types of bots, their usage and how bots have impacted the Software Security. Apart from using Bots to provide services to the user, bots are also used to spread malware and hijack distributed computer networks, compromising critical information. The paper also proposes some measures to enhance the security of bots.
Towards an innovative model in wearable expert system for skiing
Research Conference on Metadata and Semantics Research (MTSR 2020)
Elson Kurian*, Sherwin Varghese*, Stefano Fiorini
Mobile applications and portable devices are being used extensively in the healthcare sector due to their rapid development. Wearable devices having sensors can be used to collect, analyze, and transmit the vital signs of the wearer. In this paper, we have proposed a wearable expert system that supports and monitors the skier during his activity. This research work is motivated by the need to provide rapid assistance to skiers, especially during off-piste skiing, where its more dangerous, and seeking help is difficult with mishaps. Our approach mainly focuses on proposing an expert system that integrates wearable devices (helmet, goggles, digital watch) with the skier’s smartphone. We present an architecture model and knowledge artifacts to design a wearable expert system for skiing.
Analytical recommendation model using directed graphs for employee and organization
2018 8th International Conference on Intelligent Systems, Modelling and Simulation (ISMS)
Amit Sharma*, Sherwin Varghese*, Vijaya Sarathi Durvasula
Employees are important assets of an Organization. A successful organization needs to consider employees' careers, skill sets and opportunities for them to grow in different domains while aligning with its long-term vision. An organization should be able to provide ample career choices for their employees. Also, the employees should be given the liberty to choose from possible career options provided by the organization. The proposed solution involves the formation of an Analytical model to address these concerns in terms of: A. Organization: i) to predict skill set gaps of its employees for upcoming and current designations, ii) ensure organization's vision is aligned with employee's skills, iii) create opportunities for employees to explore different career options with their current skills, iv) forecast attrition and assist in internal job requisitions. B. Employee: i) to visualize career transitions and explore different career opportunities, ii) recommend skills and trainings to acquire those skills for job roles in new business areas. The solution represents attributes for designations, skills and job profile of employees for an organization based on career history that serves as data set for user-based collaborative filtering, hence recommendations can be provided for Employees and Organization. This model will improve the employee's engagement within the organization, helps to reduce the probable attritions and foster a culture of trust. Organizations can effectively understand their employees. Employees can anticipate their careers.
Patents
Database query based recommendation engine
US Patent 10,698,965
Amit Sharma*, Sherwin Varghese*, Anirban Chakraborty*
A method may include generating a first database query to retrieve user profiles from a database. The user profiles may include a first attribute and a second attribute associated with a plurality of users. Reference data may be generated based on the user profiles. The reference data may include matrix representations of the user profiles. A clustering technique may be applied to the reference data in order to determine that a first user is similar to a second user with respect to the first attribute. In response to determining that the first user is similar to the second user, a second database query may be generated to retrieve a user profile of the first user from the database. A first recommendation for the second user may be determined based on the user profile of the first user. The first recommendation may include the second attribute of the first user.
PDF 
Graph based recommendation engine
US Patent App. 15/920,363
Amit Sharma*, Sherwin Varghese*, Vijaya Sarathi Durvasula
A method for generating graph based recommendations may be provided. The method may include querying a database to at least retrieve one or more resource profiles from the database. A graph representative of the one or more resource profiles retrieved from the database may be generated. The graph representative of the one or more resource profiles may include at least one relationship between a first attribute and a second attribute included in the one or more resource profiles. A recommendation for a target user may be generated based on at least a portion of the graph representative of the one or more resource profiles. Related systems and articles of manufacture, including computer program products, are also provided.
PDF 
* denotes equal contribution
Get In Touch
Connect on