Mahesh Kumar Sahoo
(Problem Solver, Innovator, Self-Motivator, Quick Learner)
**************@*****.*** +91-966******* linkedin.com/mahesh-sahoo github.com/Msahoo876 PROFESSIONAL SUMMARY
Dynamic and innovation driven Data Engineer, Backend Engineer, AI Engineer, and Machine Learning Engineer with a Bachelor’s (BCA) and Master’s (MCA) in Computer Applications, bringing 2+ years of proven success delivering scalable backend systems, high performance data pipelines, and intelligent AI solutions for international clients. Expert in architecting AWS based data ecosystems (Glue, Lambda, Step Functions, Athena, EC2, RDS, IAM) and developing robust backend services using Python, Django, PostgreSQL, and ETL frameworks to power data driven decision making.
Specialized in machine learning, deep learning, Generative AI, NLP, and computer vision, with end to end deployment experience transforming raw data into actionable insights and automation. Published researcher with multiple Springer publications and a strong portfolio of 15+ high impact projects across financial analytics, healthcare diagnostics, predictive modeling, sentiment analysis, and AI powered chatbots. Recognized for analytical thinking, rapid problem solving, and translating complex challenges into elegant, high impact technical solutions. Thrives in remote, cross functional Agile teams, combining academic excellence, technical mastery, and creative innovation to deliver measurable business results and drive organizational growth. EDUCATION
Gandhi Institute for Technology, Bhubaneswar, Odisha, India(Affiliated to BPUT University, Odisha). Master of Computer Application-MCA (CGPA: 8.51/10) 2020-2022
Tilak Maharashtra Vidyapeeth, Pune, Maharashtra, India. Bachelor of Computer Applications-BCA (CGPA: 8.48/10) 2017-2020
Shaheed (Junior) Mahavidyalaya, Barapur, Bhadrak, Odisha, India. Xii: Council Of Higher Secondary Education (Percentage: 49.5%) 2015-2017
Satya Nanda High School, Soro, Balasore, Odisha, India. X: Board Of Secondary Education (Percentage: 62%) 2014-2015 EXPERIENCE
Vector ML Analytics New York, USA
AI Engineer (Remote) 06.2025 – 09.2025
• Designed and deployed AI agents and Generative AI bots for financial analytics and automation.
• Created an MCP server enabling seamless integration between AWS, PostgreSQL, and GitHub for automated workflows. Built universal AI agent frameworks for multi-client use cases. Data Engineer (Remote) 12.2024 – 09.2025
• Engineered and optimized scalable AWS-based data pipelines leveraging Glue, Lambda, Step Functions, Athena, EC2, RDS, IAM, and other AWS services to process large-scale datasets efficiently.
• Developed robust backend services using Django and PostgreSQL to support data-driven financial applications.
• Collaborated with 3–4 enterprise clients to build custom financial models, leveraging domain-specific data pipelines and ML solutions. Implemented Gen AI-based features to enhance automation and analytical insights across financial datasets.
• Actively contributed to Agile sprints and sprint planning using Jira; improved team throughput by streamlining ticket resolution processes.
Technologies & Skills: Python, Django, AWS (Glue, Lambda, Step Functions, Athena, EC2, RDS, IAM, etc), PostgreSQL, ETL, ML, Gen AI, Jira.
Pinaca Technologies Hyderabad, Telangana, India Full Stack Development (On Site) 04.2024 – 05.2024
• Led backend development for web applications using Django and Flask, integrating with MS SQL Server and MongoDB for optimized data access.
• Built REST APIs and contributed to system architecture improvements to enhance performance and maintainability. Ensured seamless deployment and integration with frontend components, contributing to full-stack application delivery.
• Technologies & Skills: Python, Django, Flask, MS SQL Server, MySQL, MongoDB.
Refactor Academy Bangalore, Karnataka, India
Intern As Machine Learning Engineer (Remote) 08.2022 – 06.2023
• Designed and trained predictive models using supervised and unsupervised learning algorithms.
• Conducted advanced feature engineering, model tuning, and cross-validation to improve accuracy on real- world datasets. Delivered end-to-end solutions such as: 1. E-Commerce Data Analysis – Analyzed e commerce customer data using EDA and regression models
(L1 Lasso, L2 Ridge, Elastic Net), achieving 98% R accuracy. Project Link: GitHub. 2. Customer Segmentation for Malls – Segmented mall customers for targeted marketing strategies using K Means clustering; finalized 5 clusters with a silhouette coefficient score of 0.4486. Project Link: GitHub.
• Technologies & Skills: Python, Machine Learning(Regression Models, Boasting Techniques, Decision Tree, Rendom Forest, Clustering, SVM, PCA), Deep Learning.
Skills Cafe Pune, Maharashtra, India
Intern As Python Development (On Site) 02.2020 – 06.2020
• Developed GUI-based desktop applications using Python, Tkinter, and OpenCV.
• Built productivity tools including image processing apps and a text-based notepad for internal automation use cases. Completed 3 Projects such as:
1. Image Converter in Python to reshape images. Project Link: GitHub. 2. Image Rotation in Python to rotate images at various angles. Project Link: GitHub. 3. Notepad in Python for creating and editing plain text documents. Project Link: GitHub.
• Technologies & Skills: Python, Django, Flask, PostgreSQL, OpenCV SKILLS
Programming Languages: Python, Java, C Programming, CPP, C#.
Python Libraries & Frameworks: TensorFlow, Keras, PyTorch, Scikit-Learn, OpenCV, Django, Flask.
AI Technologies: Generative AI, Large language models (LLM), Natural Language Processing(NLP).
Machine Learning: Regression Techniques, Boosting Techniques, Decision Tree, Clustering Techniques, Random Forest, PCA, Support Vector Machines (SVM).
Deep Learning: Artificial Neural Networks (ANN), Convolutional Neural Network(CNN), Recurrent Neural Network
(RNN), Computer Vision, Image Processing, Image Analysis.
Data Management: Pandas, NumPy, Matplotlib, Seaborn, Data Structure, Data Cleaning, Data Analysis, ETL Pipelines, Financial Data Analysis, Data Visualization.
Database and Cloud: Oracle, PLSQL, SQL, MySQL, PostgreSQL, NoSQL, MongoDB, Google Firebase, AWS (Glue, Lambda, Step Functions, Athena, EC2, RDS, IAM, etc).
Dev Tools: Git, Docker, Jira.
PUBLICATION
Diagnosis of Plant Diseases By Image Processing Model For Sustainable Solutions ICISML
• Developed a predictive model for diagnosing plant diseases using image analysis. Utilized machine learning to analyze RGB images and identify diseases, recommending sustainable solutions.
• Employed Convolutional Neural Networks (CNNs) and the VGG19 model for accurate disease detection, creating an effective AI framework for plant health diagnosis.
• Springer link of my published paper: link.springer.com/published-paper
• Certificate: drive.google.com/ICISML
Empirical Analysis of Contextual Factors in Native Mobile App Development: A Case Study of E-Commerce Applications
BITMDM
• Investigated the impact of contextual factors (device, user behavior, mobility, and social data) in the development of native e-commerce apps.
• Built a process model for mobile app development validated using customer feedback and statistical ML methods.
• Springer link of my published paper: link.springer.com/published-paper PROJECTS
Breast Cancer Tumor Classification (Research Paper):
• Built a diagnostic tool to classify tumors as benign or malignant using machine learning algorithms like SVM, Logistic Regression, and Random Forest, aiding early detection and treatment planning.
• Technologies used: Python, Scikit-learn, Pandas, ML Algorithms, Data Analysis.
Diabetes Prediction:
• Developed a predictive health model using the Indian diabetes dataset and Logistic Regression with Grid Search to identify high-risk individuals. Optimized model performance through hyperparameter tuning.
• Technologies used: Python, Scikit-learn, GridSearchCV, Pandas, ML Techniques. Project Link: GitHub
Customer Reviews Rating Analysis:
• Processed and analyzed over 2 million e-commerce reviews using sentiment analysis and machine learning
(AdaBoost and XGBoost) to derive actionable insights for improving product strategies.
• Technologies used: Python, XGBoost, AdaBoost, NLTK, TextBlob, Data Visualization Project Link: GitHub
30 Years of Stock Market Data Analysis:
• Performed trend analysis and forecasting on three decades of stock data using Yahoo Finance API and regression models to uncover investment insights and market behavior.
• Technologies used: Python, Pandas, Matplotlib, ML, Regression Models, Data Analysis. Project Link: GitHub
Credit Card Customer Performance Analysis:
• Created a predictive model to classify banking customers by profitability to support retention and strategic targeting using supervised ML algorithms.
• Technologies used: Python, Machine Learning, Data Analysis. Project Link: GitHub
News Summarization & Sentiment Analysis Application:
• Developed an NLP-powered app that summarizes global news articles and detects sentiment using pre-trained models and APIs like Hugging Face, TextBlob, and OpenAI.
• Technologies used: Python, Natural Language Processing(NLP), TextBlob, OpenAI. Project Link: GitHub
Historical Chatbot Application (Still Working):
• Building a document-aware chatbot that answers historical questions using LangChain and Pinecone for semantic search, integrating OpenAI’s LLMs for natural conversation.
• Technologies used: Python, Large language models (LLM), Pinecone, OpenAI, Vactor DB.
Delivery Process Improvement:
• Enhanced logistics operations for U.S.-based delivery services using geolocation event data and machine learning to predict delivery delays and streamline routing.
• Technologies used: Python, Pandas, Machine Learning, Data Analysis. Project Link: GitHub
Ez2Learn – Online Learning Portal (Live Project):
• Developed a comprehensive e-learning platform offering technology courses with user progress tracking, interactive learning modules, and admin control panels.
• Technologies used: HTML5, CSS3, JavaScript, React.JS, Python, Django, PostgreSQL.
Let's go to odisha tourism(Live Project):
• Built a smart tourism platform that curates and customizes travel plans across Odisha, with a dynamic interface, interactive maps, and personalized tour packages.
• Technologies used: HTML5, CSS3, JavaScript, React.JS, Python, Django, PostgreSQL, Data Visualization.
Tour guides assign management:
• Created a centralized system to allocate local guides based on tourist bookings, improving experience quality and management efficiency.
• Technologies used: HTML5, CSS3, JavaScript, React.JS, Python, Flask, MSSQL. Project Link: GitHub
Task Management System:
• Designed a productivity web app for managing personal and team-based tasks, including categorization, deadlines, and real-time updates.
• Technologies used: HTML5, CSS3, JavaScript, React.JS, Python, Django, MongoDB. Project Link: GitHub
Video call one to one meeting:
• Built a secure, real-time video communication platform with authentication, messaging, and live streaming for remote meetings.
• Technologies used: HTML5, CSS3, JavaScript, React Native, Node.JS, Google Firebase. Project Link: GitHub CERTIFICATION
TCS ION NQT – IT: Certificate.
NPTEL IIT CERTIFICATES:
• Programming in JAVA: Certificate.
• Internet Of Things(IOT): Certificate.
• Cloud Computing: Certificate.
• Software Project Management: Certificate.
HACKER RANK CERTIFICATES:
• Programming in Java: Certificate.
• Programming in Python: Certificate.