Skip to content
View ara-5's full-sized avatar

Block or report ara-5

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
ara-5/README.md

Athira Anil Kumar

AI Engineer · Generative AI · Agentic AI Systems · LLM Security · AI Red Teaming

MSc Cyber Security (Distinction) · IEEE-Published Researcher · Sharjah, UAE

Portfolio · LinkedIn · Email

What I build

I work at the intersection of capable AI and secure AI — production-grade agentic/RAG systems, and the red-teaming frameworks that stress-test them. Currently a GenAI Security Testing Developer at Cosmic Info Solution, evaluating LLM systems against prompt injection, jailbreaks, and system-prompt extraction.

  • 🔍 Enterprise-Agentic-RAG-Platform — LangGraph agentic loop, hybrid BM25+FAISS retrieval, Corrective RAG with web fallback. RAGAs Faithfulness 0.91 / Relevancy 0.88, gated in CI/CD.
  • 🛡️ Capstone-Agent (CodeSentinel) — Five-agent system that debates, reaches consensus, and patches security vulnerabilities in code, with auto-generated reports.
  • 🧠 mind-mri-agent-second-brain — Zero-dependency, offline-first Graph-RAG memory core for autonomous agents; cuts LLM context input 95–99% vs. flat-RAG.
  • 📡 TrustMesh — Agentic SIM-swap fraud detection using telecom CAMARA network APIs.

Research

"Detecting Human-Written and AI-Generated Phishing Emails Using DistilBERT and Explainable AI" — IEEE, 2025. Tri-class classifier (~98% accuracy) with SHAP/LIME explainability. Read it →

Stack

LangGraph LangChain FAISS BM25 RAGAs Transformers DistilBERT FastAPI Docker PPO Stable-Baselines3 Python JavaScript

Open to AI Engineer / GenAI Engineer / AI Security roles — UAE, hybrid, or remote.

Pinned Loading

  1. mind-mri-agent-second-brain mind-mri-agent-second-brain Public

    A zero-dependency, offline-first Graph-RAG memory core and REST API server for autonomous AI agents. Features vector-like TF-IDF semantic search, exponential time-decay relevance scoring, and an in…

    JavaScript

  2. Enterprise-Agentic-RAG-Platform Enterprise-Agentic-RAG-Platform Public

    Agentic RAG system with LangGraph, hybrid BM25+FAISS retrieval, cross-encoder reranking, Corrective RAG, FastAPI, RAGAs evaluation, and Docker deployment

    Python 4 1

  3. Automated-threat-intel-feed Automated-threat-intel-feed Public

    Fully automated AI-powered cybersecurity threat intelligence feed using Python and GitHub Actions

    Python 1

  4. AI-Content-Brief-Workflow AI-Content-Brief-Workflow Public

    Four-stage AI pipeline that turns any topic into a production-ready content brief — intent analysis, outline, drafting, and quality scoring.

    JavaScript

  5. ai-operations-assistant ai-operations-assistant Public

    A multi-agent AI system powered by Claude Sonnet. Routes business questions through Manager → Research → Analysis → Report agents via LangGraph and FastAPI.

    Python

  6. Capstone-Agent Capstone-Agent Public

    CodeSentinel — multi-agent AI system for automated code security review, patch generation, and reporting (Google ADK + Gemini)

    Python