Hello!

I'm Shauryaman Sawai



My Instagram My Linkedin

Name: Shauryaman Sawai

Job Role: Full-Stack Developer / Data Analyst / Generative AI (Gen AI)

College: National Institute of Technology, Rourkela

Skills

Machine Learning (ML)
Generative AI (GenAI)
Django REST Framework
Python
Power BI
SQL
Data-Analytics / Business Research

About

About Me

I’m a student at the National Institute of Technology with a deep enthusiasm for Machine Learning and deriving insights from data. I enjoy coding in Python, especially for web development, where I create, deploy, and integrate scripts into web applications. My passion lies in combining data-driven approaches with software development to build solutions that solve real-world problems.

  • Profile: A passionate Machine Learning Enthusiast, experienced Python Developer, and detail-oriented Data Analyst.

  • Domain: Software Developement and Analytics

  • Education: Bachelors of Teachnology

  • Language: English, Hindi

  • Other Skills: Research and Analytics, Problem Solving, Creativity, Knowledge of art fundamentals, Technical proficiency, Communication skills, Time management, Adaptability & Attention to detail

  • Interest: Traveling, Watching Movies, Coding, E-sports Gamming

LinkedIn

Resume

Resume

Machine Learning and Data Science enthusiast with a passion for extracting actionable insights from data and developing intelligent, scalable solutions. Proficient in Python and Django for full-stack web development, specializing in building, deploying, and integrating scripts into dynamic web applications. Skilled in Generative AI (GenAI), with expertise in tools like Hugging Face Transformers, OpenAI APIs, and fine-tuning models for custom applications. Hands-on experience with machine learning frameworks such as TensorFlow and Scikit-learn, and proficient in data analysis tools including Pandas, NumPy, and SQL. Adept at leveraging advanced AI/ML models and data pipelines to solve complex problems and create impactful, data-driven applications that meet real-world demands.

Internships


December(2024)-May(2025)

Tech Intern

Market Scope

During my internship at Market Scope, I focused on developing AI-driven solutions to automate and optimize recruitment and hiring processes. My primary contribution was building a resume ranking model that utilized natural language processing (NLP) techniques and the cosine similarity function to quantify the relevance of resumes against job descriptions, enabling efficient and data-driven candidate shortlisting. Additionally, I developed a smart resume parsing system that leveraged named entity recognition (NER) and rule-based extraction to accurately extract, classify, and structure key candidate information, enhancing data integrity and usability. To support seamless data handling, I designed and implemented a scalable data management system, incorporating relational database design and indexing techniques to ensure optimized query performance and retrieval efficiency. This internship provided me with hands-on experience in machine learning, NLP, information retrieval, and database management, reinforcing my ability to develop intelligent automation solutions within the HR tech domain.

November-December(2024)

GenAI Solution Developer

Botter Solutions Pvt Ltd.

    I worked on implementing cutting-edge solutions in the field of Natural Language Processing (NLP), focusing specifically on fine-tuning embeddings using Hugging Face Transformers. My primary contribution was the development and optimization of a PyTorch-based model that incorporated a custom linear layer for domain-specific tasks. Built a text extraction pipeline to process content from 100+ PDFs and 50+ web pages using Python libraries like pdf2 and BeautifulSoup4. Extracted and tokenized 10,000+ sentences from PDFs, implementing preprocessing steps such as stop-word removal and text normalization to enhance model input quality. Prepared a labeled dataset of 5,000+ sentence pairs for fine-tuning embeddings. Designed a custom embedding model with a linear layer on a Hugging Face pretrained model, achieving a 15% improvement in semantic similarity tasks.

March-May(2024)

Django Backend Developer Intern

TBH

To Be Honest, a subsidary of Tatsya.com , specializes in Back-End Developement, Data Analytics and creating Machine Learning Models. We craft custom software solutions to enhance functionality and productivity across industries.

  • Working on Backend-Developement for applications Development for TBH based Django-Rest frame work.
  • Experience of working in Postgre Sql Server.
  • Integrated third-party APIs and services, handling authentication and data processing to enrich backend functionality.
  • Collaborated with frontend developers to ensure smooth API consumption.

August-September(2024)

Research and Analytics focused on SMB

Seaport AI

During my research and analytics work focused on Small and Medium Businesses (SMBs), I conducted in-depth analysis on the challenges faced by SMBs in scaling their operations, accessing resources, and improving profitability. I used data-driven insights to identify key obstacles such as limited access to funding, inadequate technology adoption, and market competition. My analysis helped in crafting strategic recommendations to improve business efficiency, optimize resource allocation, and develop targeted solutions aimed at supporting SMB growth and sustainability.

  • Conducting market research and competitor analysis.



Education


2023-2028

Bachelor of Technology

National Institute of Technology , Rourkela

Grade: First class distinction.

2022-2023

Higher Secondary School

CBSE (PCM)

Grade: First class distinction.

Download CV

Here's my

I love to code & Wrangling Data.


Projects

My Projects

Explore some of my work below.

Snap_Jini

Built a Generative AI web app that creates social media posts with captions, hashtags, and images based on user prompts. Integrated OpenAI & Pexels APIs for content generation and visuals. Developed with Next.js, Django, and Django REST API, enabling real-time customization and interactive editing.

Smart Resume Parser & Data Manager

Built an AI-powered system to automate resume parsing, data extraction, and storage in Excel via App Sheet API. It accurately identifies key candidate details and features an interactive review interface for refinement, enhancing HR efficiency and data accuracy while reducing manual effort.

Open Library Project

Open Library Project! This Django-based web app lets users explore and contribute to a collection of books and blogs. Features include user authentication for logging in, signing up, and managing accounts, as well as the ability to add personal blogs.

Health Track (Blood Sugar Prediction)

Health Track offers personalized diet plans and a Random Forest model predicting blood sugar with 65% accuracy. It also features an AI chatbot for instant health support.

Shelter Map

SHELTER MAP is a web application designed to provide real-time assistance during natural disasters. It integrates data from multiple sources, including the OCHA database and satellite imagery, to offer accurate and timely information during emergencies.

Dynamic Pricing Algorithm.

Developed a real-time pricing solution using Google Maps, Yelp, and OpenWeatherMap APIs, analyzing data from 50+ competitors. Integrated dynamic pricing based on weather and traffic, achieving 80% accuracy in optimized menu price predictions, increasing revenue.

Sentiment-Analysis-of-Hotel-Reviews

Implemented a lexicon-based sentiment analysis using TextBlob to classify 10,000+ customer reviews into positive, negative, or neutral categories, providing actionable insights to improve customer satisfaction and enhance business strategies.

Interactive Sales Dashboards (Power BI)

Developed 4 interactive dashboards using Microsoft Power BI to visualize and analyze sales data across multiple regions, enabling real-time insights and improving sales performance tracking.

WEB SCRAPING

Extracted 1,000+ words of textual data from Blackcoffer web articles and performed text analysis to compute variables such as Positive Score, Negative Score, and Polarity Score. Achieved 95% accuracy in sentiment classification using NLP techniques and Python libraries like NLTK and TextBlob.

Contact

Contact Me

Below are the details to reach out to me!

Address

Rourkela, Odisha

Contact Number

+91 8278799141

Email Address

sawaisushil@gmail.com

Download Resume

resumelink



Have a Question?