Open to Work Leicester, UK UK Student Visa · Tier 4 · PSW Eligible Available Immediately

Kornu Venkata
Santosh Kumar

Turning messy data into decisions that matter

MSc Data Science at University of Leicester — building production-ready ML pipelines, deep learning models, and interactive dashboards. Passionate about making data science that actually moves the needle for organisations.

Open to remote, hybrid & on-site
UK-wide & international relocation
Internships · Graduate roles · Full-time
8+
Projects
96%
Best Accuracy
213k+
Records Analysed
5
Certifications

Who I am

Introduction

I'm an MSc Data Science candidate at the University of Leicester, passionate about transforming complex datasets into decisions that drive real business value. My work spans the full pipeline — from raw data wrangling and EDA to deploying production-ready ML models.

Background

With a B.Tech in Electronics & Communication Engineering from IIIT Kalyani, I bring a rigorous engineering mindset to data science challenges — whether forecasting urban traffic with LSTM networks, analysing 213k+ public-sector spending records, or building NLP classification systems.

Industry Experience

I've worked with Vodafone Idea Foundation (_VOIS) as a Data Analytics Intern, applying AI & LLM pipelines to generate actionable business insights from real-world datasets — delivering analysis reports and supporting data-driven decisions.

Core Expertise
Python · ML Pipelines Deep Learning (LSTM · CNN · GRU) Statistical Analysis Tableau · Power BI NLP & Text Classification Feature Engineering EDA & Data Wrangling Scikit-learn · PyTorch GenAI & LLMs SQL & PySpark
Opportunities

I'm open to remote, hybrid, on-site, and relocation opportunities across the UK and globally. I thrive in fast-paced environments where data is used to drive real decisions, and I'm available to start immediately.

Leicester, UK Open to Relocate Remote · Hybrid · On-Site Data Science Intern ML Engineer Graduate Roles Full-Time
Available Immediately
UK Student Visa (Tier 4)
PSW Graduate Visa Eligible
Sponsorship Welcome
International Relocation Ready

Skills & Technologies

Languages

Programming

PythonRSQLPySparkC
ML Libraries

ML & Data

PandasNumPyScikit-learnPyTorchTensorFlowTidyverseggplot2
Deep Learning

Neural Networks

LSTMGRUCNNMLPTransformersNLP
Visualisation

Dashboards & BI

TableauPower BIExcelDatawrapperFlourishiNZight
Mathematics

Statistics & Maths

Linear AlgebraProbabilityCalculusSignal ProcessingEDAHypothesis Testing
Methods

ML Techniques

RegressionClassificationTime SeriesFeature EngineeringHyperparameter TuningCross-Validation
Data Engineering

Data Preparation

Data WranglingData LabelingStatistical AnalysisData CleaningData ImputationPipeline Design
AI Tools

GenAI & LLMs

LLM PromptingRAGOpenAI APILangChainAgentic AI
Tools

Dev & Workflow

GitGitHubJupyterVS CodeGoogle ColabAzure

Projects

★ Featured Strongest business-impact projects, selected by recruiter relevance
Machine LearningFraud Detection2025

FraudSentinel

Real-Time Financial Fraud Detection System

Financial institutions lose $40B+ annually to fraud. Rule-based systems miss emerging patterns and generate false positives that hurt customer experience.

End-to-end ML pipeline using SMOTE oversampling, ensemble classifiers (RF + GBM), and threshold optimisation. Delivered reduced false-positive rate with high precision, designed for real-time inference.

↓ FPRFalse Positives
↑ F1Score
Real-TimeInference
PythonScikit-learnSMOTEEnsembleFeature Engineering
ClassificationHealthcare MLJul 2023

Breast Cancer Prediction

Early Detection ML System — 96% Accuracy

Breast cancer misdiagnosis is preventable. High-dimensional clinical datasets need careful feature selection to maximise recall without overfitting.

Led a 3-person team benchmarking Logistic Regression, Random Forest, SVM, and neural networks. Applied SMOTE, k-fold cross-validation, and hyperparameter grid search. Achieved 96% accuracy with high recall.

96%Accuracy
HighRecall
4 ModelsBenchmarked
PythonScikit-learnTensorFlowSMOTEGrid Search
Deep LearningTime SeriesJul 2024

Traffic Flow Prediction

LSTM · GRU · MLP — 89% Accuracy, RMSE −15%

Urban congestion costs cities billions in lost productivity. Traditional statistical models can't capture non-linear temporal dependencies in real-time sensor streams.

Designed and benchmarked LSTM, GRU, and MLP architectures on traffic sensor data with early stopping, learning-rate scheduling, and systematic hyperparameter search. Reduced RMSE by 15% vs. baseline.

89%Accuracy
−15%RMSE
3 ArchsCompared
PythonPyTorchLSTMGRUMLPTime Series
Data AnalysisDashboardNov 2025

Birmingham Council Spending

Public Sector Analytics — 213,000+ Transactions

Birmingham City Council needed transparent, accessible analysis of its spending distribution to support budget accountability and policy planning.

Cleaned and reconciled 213k+ transaction records, engineered supplier and department-level aggregations, and built a fully interactive Excel dashboard with Pivot Tables and KPI cards. Surfaced that Housing = 26% of spend.

213k+Records
26%Housing Spend
InteractiveDashboard
ExcelPivot TablesData WranglingStorytelling
All GitHub Repositories

Live from GitHub API · non-fork · sorted by last updated

View Profile →
Fetching repositories from GitHub…
GitHub Activity @venkatakornu-eng
Public Repos
Followers
Total Stars
Top Language
GitHub contribution heatmap

Experience & Education

Work Experience
Oct 2025
Vodafone Idea Foundation (_VOIS)
Data Analytics Intern – AI & LLMs · Remote, India
  • Conducted a data analysis case study in the science & technology domain; authored an insight report using LLM assistance
  • Analysed multiple datasets using AI/ML pipelines to surface actionable business insights
  • Applied feature engineering, predictive modelling, and data processing techniques across real-world datasets
  • Gained experience with agentic AI workflows and responsible AI principles
2024
Research Team Lead
MSME Communication Barriers Study · Academic Research
  • Led a 5-member research team investigating communication inefficiencies in the textile non-woven MSME sector
  • Designed, distributed, and analysed 72 structured professional surveys
  • Delivered statistical insights and recommendations to industry stakeholders
Education
2024–25
University of Leicester
MSc Data Science · United Kingdom
Modules: ML, Deep Learning, NLP, Big Data, Data Viz, Statistical Methods
2017–21
IIIT Kalyani
B.Tech — Electronics & Communication Engineering
GPA 7.40 / 10
2019
Sri Chaitanya Junior Kalasala
High School, MPC · Hyderabad, India
GPA 9.34 / 10

Certifications & Training

Deloitte Australia · Forage
Data Analytics Job Simulation
July 2025
  • Data analysis and forensic technology simulation
  • Built a Tableau dashboard to communicate business insights to stakeholders
  • Transformed Excel data for classification and strategic decision-making
View on LinkedIn
Tata Group · Forage
AI-Powered Data Analytics Simulation
September 2025
  • EDA using GenAI tools; assessed data quality and risk indicators
  • Proposed a no-code predictive framework for customer delinquency risk scoring
  • Designed an agentic AI collections strategy with ethical AI compliance
View on LinkedIn
Boston Consulting Group (BCG) · Forage
Introduction to Data for Decision Makers
2025
  • Completed BCG's job simulation on applying data-driven thinking to business decisions
  • Developed frameworks for translating complex data insights into strategic recommendations
  • Practised communicating analytical findings to non-technical executive stakeholders
View Certificate
Goldman Sachs · Forage
Risk Job Simulation
2025
  • Completed Goldman Sachs' risk analytics simulation in financial services
  • Assessed credit and operational risk indicators using structured financial datasets
  • Developed risk-aware analytical thinking aligned with investment banking standards
View Certificate
Coursera · Verified Certificate
Coursera Certification
2025 · ID: 8RFPBQ2ZTE7J
  • Completed a verified online certification programme via Coursera
  • Demonstrated proficiency in a structured, self-paced learning curriculum
  • Certificate independently verifiable via Coursera's credential verification system
Verify Certificate

Achievements & Extra

Academic
MSc Data Science — University of Leicester
Pursuing a postgraduate degree in the UK, demonstrating adaptability and commitment to advancing in data science at an international institution.
Industry Experience
Vodafone Idea Foundation — Data Analytics Intern
Selected for an AI & LLM-focused data analytics internship at one of India's largest telecom companies, applying ML pipelines to real business datasets.
Research Leadership
5-Member Research Team Lead
Led end-to-end industry research across 72 professional surveys, developing skills in survey design, team coordination, and statistical interpretation.
Competitions
Kaggle & Hackathons
Actively participating in Kaggle competitions and ML hackathons to sharpen competitive data science skills. Add your Kaggle profile link and competition results here.
Publications & Blog
Technical Writing
Sharing data science knowledge through articles and case studies. Add your Medium, Towards Data Science, or personal blog links here to showcase thought leadership.
Open Source
Open-Source Contributions
Contributing to open-source data science tools and repositories. Add your notable PRs, library contributions, or open-source projects here as they develop.

Let's build
something data-driven
together.

Open to data science internships, graduate roles, and full-time positions. Based in Leicester, UK — available for remote, hybrid, on-site, and relocation. Available immediately.

Download CV / Resume
Prefer a quick call? Drop me an email and I'll respond within 24 hours to arrange a time that works.
Email Me →