OPEN TO OPPORTUNITIES · BENGALURU, INDIA
Lakshitha
Loganathan
Build. Learn. Repeat.
>

I'm a Computer Engineering student specializing in AI/ML, with a passion for building end-to-end systems.

8.8
GPA / 10.0
6+
HACKATHONS
2nd
HACK DAYS 2026
SCROLL
01 ABOUT

Exploring AI Beyond Accuracy

Final-year Computer Engineering student at EPCET Bengaluru, specializing in Artificial Intelligence and Machine Learning, with a GPA of 8.8/10.

I work at the intersection of AI, machine learning, and scalable software engineering — transforming complex data into systems that are practical, resilient, and built for real-world impact. My focus goes beyond training accurate models; I'm driven by designing intelligent solutions that remain reliable under uncertainty, adapt to imperfect data, and perform consistently in production environments.

I compete in hackathons to stress-test my speed and adaptability, and I thrive on learning new tools and techniques that push the boundaries of what's possible with data.

Python TensorFlow PyTorch scikit-learn Hugging Face SMOTE Random Forest Tableau MySQL MongoDB Power BI Git
Curious Learner
Driven by curiosity to understand how models learn, adapt, and improve through data.
Deep Problem Solver
Breaking complex problems into structured, scalable solutions with clear reasoning and execution.
Exploration Driven
Eager to experiment with new techniques and push the boundaries of what's possible.
$ python evaluate_model.py ✓ ROC-AUC : 0.9731 ✓ F1-Score : 0.9600 ✓ Minority-class recall : +23% Model pipeline validated. Ready for production.
02 FEATURED WORK

Built to measure and improve

Real pipelines, real data, real evaluation. Not tutorials — systems engineered to perform under pressure.

🏆 2nd Place — Hack Days 2026 · 8-Hour Sprint
ZeroVA AI - Zero Day Vulnerability Analysis
CodeBERT · GNN · XGBoost · LightGBM · FastAPI · Docker · Hugging Face Spaces

A production-grade AI security platform that predicts zero-day vulnerabilities in source code before they're exploited. Built under an intense 8-hour hackathon constraint, ZeroVA combines a fine-tuned CodeBERT transformer for semantic code understanding, a Graph Neural Network to model inter-function dependencies, and a 4-model ensemble (XGBoost, LightGBM, CatBoost, Random Forest) trained on 8,000 CVE-annotated samples. The system is fully deployed via FastAPI on Hugging Face Spaces with Docker.

97.3% ACCURACY
98.1% AUC-ROC
8K CVE SAMPLES
Python CodeBERT GNN XGBoost LightGBM CatBoost FastAPI Docker Hugging Face
Quillox - AI Assistant With Tone Control
LLM (Meta LLaMA 3.3 70B) · Node.js · Express.js · Groq · NLP · Render

A full-stack AI writing assistant powered by Meta's LLaMA 3.3 70B, designed to generate contextually aware content across 8 distinct tones, 7 audience profiles, and 7 output formats — from technical documentation to persuasive copy. Quillox includes a production-grade AI safety layer with prompt injection detection and jailbreak filtering to prevent misuse, plus a daily token quota system to manage inference costs. Deployed on Render with GitHub auto-deploy for continuous delivery.

8 TONE MODES
7 AUDIENCES
7 OUTPUT FORMATS
Node.js Express.js LLaMA 3.3 70B Groq API Prompt Engineering NLP Render GitHub CI/CD
Phishing URL Detection Engine
Ensemble Stacking · 95,000+ URLs · Lexical + Statistical Feature Engineering

Architected a classification pipeline across 95,000+ URLs using lexical and statistical feature extraction with Python and scikit-learn. Benchmarked six models end-to-end; Random Forest achieved a 0.96 F1-score while ensemble stacking reached 0.91 macro F1 on completely unseen data. Applied SMOTE to correct severe class imbalance and maximize zero-day phishing detection.

95K+ URLs PROCESSED
0.96 RF F1-SCORE
0.91 ENSEMBLE F1
Python scikit-learn Random Forest Ensemble Methods SMOTE NLP Features Pandas Matplotlib
03 EXPERIENCE

Where I've shipped things

2026
Bengaluru
Leadership
Campus Ambassador
Women Who Master 2026 — Aspire For Her × Logitech
Selected as Campus Ambassador for Women Who Master 2026, India's largest women-only national hackathon, organised in collaboration with Aspire For Her, Logitech, and AICTE
Drove campus-wide awareness and registrations, representing the initiative across EPCET and mobilising student participation at scale
Acted as the on-ground bridge between event organisers and student community, coordinating outreach and providing first-point support for prospective participants
Jan 2026 — Mar 2026
Bengaluru
Training
AI / ML Trainee
ISM UNIV
Built and validated a house price prediction model using Python, scikit-learn, and Pandas as part of guided applied projects
Implemented complete data preprocessing workflows including missing-value handling, encoding, and normalization
Completed end-to-end ML lifecycle: EDA → feature engineering → model training → evaluation → iteration
Deepened applied understanding of the Developing AI Model using Python curriculum
Oct 2024 — Dec 2024
Bengaluru
Internship
Machine Learning Intern
Placemantra
Designed an online fraud detection system on real-world payment transaction data with custom transaction-level feature engineering
Applied SMOTE oversampling to address severe class imbalance, improving minority-class recall by ~23% on test data
Architected a structured, reproducible ML pipeline: preprocessing → stratified splitting → model training → evaluation
Optimized classification performance using ROC-AUC and F1-score as primary evaluation metrics to minimize false positives
🏆 2nd Place
Hack Days 2026
100+ Teams · 8-Hour Sprint
1st Runner Up
8H SPRINT AI SECURITY WINNER

Won 2nd place among 100+ competing teams by building ZeroVA AI — a production-grade security platform combining CodeBERT, a Graph Neural Network, and a 4-model ML ensemble that achieved 97.3% accuracy on CVE-annotated code samples.

USAII® Global AI Hackathon 2026
Global Virtual Hackathon
Ranked 286 of 424 Teams in 6000+ Participants
GLOBAL COLLEGE TRACK 6000+ PARTICIPANTS

Competed in the College Track of the USAII® Global AI Hackathon 2026, placing 286th out of 424 teams among over 6,000 global participants, demonstrating applied AI/ML skills on an international stage.

Future of Work — 24H Hackathon
TGB × Kroolo
Top 100
24H SPRINT GENERATIVE AI SHORTLISTED

Developed an AI-driven productivity solution using Generative AI for workflow automation and task optimisation. Shortlisted in the national top 100, competing against working industry professionals.

Replit Vibeathon
Global Competition
Top 1,000
36H GLOBAL 1000+ TEAMS ML

Selected among 1,000+ global participants. Built an AI-based mental health application leveraging machine learning for personalised user recommendations.

Vibe Hack 2.0
Virtual Hackathon
Top 5,000
8H SPRINT 25,000+ TEAMS AI/ML

Advanced to Top 5,000 out of 25,000+ teams globally. Developed a rapid AI/ML prototype under 8-hour constraints, focusing on real-time problem solving.

Code Craze — VertechX 12.0
National Coding Competition
Final Round
NATIONAL DSA ALGORITHMS

Final Round qualifier in a national-level coding competition, demonstrating strong problem-solving skills using data structures and algorithms.

B.E. Computer Engineering — AI/ML Specialization
East Point College of Engineering and Technology, Bengaluru
8.8 / 10.0
Sep 2023 — Expected 2027
Pre-University — PCMC + Computer Science (French)
Jyoti Nivas PU College Autonomous, Bengaluru
82.3%
2021 — 2023
SSLC — Class 10
Air Force School, ASTE, Murugeshpalaya GV Camp
81.5%
2009 — 2021
CS50x 2025
Harvard University (edX)
Introduction to Machine Learning
NPTEL
Machine Learning in Python
Infosys Springboard
Developing AI Models with Python
ISM UNIV
Introduction to Cyber Security
Cisco
Python Data Structures & Algorithms
Infosys Springboard
JavaScript Course with Certification
Scaler
Getting Started with ML in Python
Infosys Springboard
04 SKILLS

The technical stack

Tools and techniques I use to build, evaluate, and deploy machine learning systems.

AI & ML
Supervised Learning90%
Random Forest / Ensembles88%
Feature Engineering85%
Class Imbalance (SMOTE)85%
Model Evaluation (F1 / AUC)87%
NLP / Text Classification72%
{ }Languages & Libraries
Python92%
scikit-learn / Pandas / NumPy88%
TensorFlow / PyTorch68%
Hugging Face Transformers62%
Java / C++60%
JavaScript58%
Data & Visualization
Pandas / NumPy88%
Matplotlib / Seaborn80%
Tableau70%
Power BI65%
MySQL72%
Tools & Workflow
Git / GitHub80%
Jupyter / VS Code88%
Data Pipeline Design82%
Experiment Tracking70%
SPOKEN LANGUAGES
English — Fluent
Hindi — Professional
Tamil — Native
French — Professional
05 CONTACT

Let's build something intelligent

Actively seeking AI/ML engineering roles, research collaborations, and internship opportunities. Whether you have a model to train or a pipeline to build — let's talk.