M karthikesh
AI/ML Engineer · Systems Builder
Hyderabad, India
I build AI-powered systems that turn complex problems into practical, reliable software. My work spans machine learning, intelligent routing, applied NLP, and full-stack engineering. I’m currently exploring reasoning systems, adaptive planning, and the engineering challenges involved in making AI useful beyond a demo. Projects include ECRS, an experimental cognitive routing system for language-model reasoning, and LifeOS, a personal operating system combining scheduling, learning, health, and long-term goal planning. Currently focused on strengthening my foundations in computer science, preparing for GATE CS & DA, and building systems that are technically rigorous and useful in the real world. Open to connecting with developers, researchers, and builders working on AI, systems, and ambitious engineering projects.
Frontend Developer Intern
Tribha Digital Solutions
- Developed and deployed responsive web interfaces using React, Vite, and Tailwind CSS. Designed modular, reusable UI components, integrated Git-based continuous deployment through Netlify, and resolved layout and routing inconsistencies to improve rendering stability and responsiveness.
Real-Time API Abuse & Anomaly Detection System
Architected a 3-layer real-time defense framework combining deterministic rules, statistical EWMA/Isolation Forest, and an unsupervised PyTorch Autoencoder + LSTM network for detecting previously unseen behavioral anomalies. Engineered an in-memory Redis feature extraction pipeline processing 30+ dynamic attributes, achieving <15ms average latency (p95 <22ms) and 91.3% precision on simulated attack benchmarks. Developed an interactive dashboard for real-time traffic monitoring, confusion matrix tracking, and live threat telemetry.
Hybrid Sentiment Analysis System
Engineered a hybrid NLP architecture integrating pretrained transformer RoBERTa with VADER rule-based sentiment scoring using confidence-aware dynamic weighting. Implemented test-time augmentation with text normalization variants to improve robustness on ambiguous samples. Achieved 96.4% accuracy and 0.95 F1-score on the IMDB benchmark dataset, outperforming the standalone RoBERTa baseline by 4.2%; deployed a Telegram bot interface for real-time scoring.
Attendee · Oct 24, 2026