GenAI & Security Engineer building production multi-agent systems and autonomous security frameworks using LangGraph, FastAPI, and modern LLM stacks. Expertise at the intersection of agentic AI orchestration and offensive security - applied to agent guardrails, tool isolation, and agentic WAPT. Background spans RAG pipelines, MCP-based tool integration, and web application penetration testing.
Architected a dual-planner autonomous WAPT framework using LangGraph with a strategic phase manager and tactical task generator, implementing adaptive plan-execute-replan loops across recon, enumeration, vuln analysis, exploitation, and reporting phases. Built a persistent LLM-based vulnerability advisor that nudges the tactical planner toward unchecked high-value attack surface (XSS, SSTI, CORS, Git exposure) every cycle across all phases, enforcing breadth-first coverage. Engineered a dependency-aware parallel executor using asyncio.gather with topological task ordering, reducing per-phase cycle count by 3-5x. Built specialised agents for Nmap, HTTP inspection, directory enumeration, XSS validation, and custom scripting, backed by MCP execution layers with shell injection prevention, scoped filesystem protections, and async background task infrastructure. Validated attack techniques and agent behavior against real-world scenarios using TryHackMe lab environments.
Personal AI Assistant Framework. Architected a multi-user AI assistant backend supporting streaming text and real-time voice interaction using FastAPI, LangGraph, and WebSockets. Designed a three-tier persistent memory system (Profile / Episodic / Semantic) backed by PostgreSQL and ChromaDB with composite retrieval scoring using semantic similarity, importance weighting, and recency decay. Implemented dual retrieval runtimes (semantic vector retrieval and lightweight lexical retrieval) switchable at runtime, built scalable agent orchestration pipelines with contextual memory injection, and containerized backend workloads on ACI integrating Groq STT, finetuned GPTSoVits TTS, and local embedding runtimes.
A basic Endpoint Detection and Response project focused on device registration and management. A Python agent collects system information (hostname, OS, serial, CPU, RAM, GPU, network interfaces) and registers devices with a FastAPI server storing to Supabase PostgreSQL. Includes a React admin dashboard with JWT authentication, logout blocklisting, and protected device endpoints.
A modular persistent memory framework for LLM agents. Provides a four-tier memory architecture backed by PostgreSQL and ChromaDB, exposed as a FastAPI REST service.
An educational web application showing how XSS and SQL Injection work. Built to teach students and beginners how insecure input handling can be exploited, with clear examples of payloads and insecure patterns.
A hand-gesture detection system that converts real-time webcam keypoints into keyboard shortcuts. Built for productivity and automation, featuring gesture recognition, shortcut mapping, and smooth real-time interaction.