← Back to home

All Projects

Twenty builds across LLM systems, RAG, computer vision, automation, voice AI, quantitative trading and governance tooling.

GOVERNANCE · OPEN SOURCE

Vigil: AI Governance Dashboard

LLM observability & safety platform: model registry with risk classification, audit logging, PII & toxicity detection, cost tracking across 250+ models, NIST AI RMF compliance reports, published Python SDK.

FastAPIReactPostgreSQLRedisDocker
RAG · LIVE

Legal Mind AI

RAG system letting legal teams query large PDF documents in natural language with source-cited answers. Supports Gemini, OpenAI and local Ollama backends.

LangChainChromaDBFastAPIReact
VOICE AI

AI Voice Calling Agent

Production outbound and inbound voice agent for automated phone qualification and warm transfer. Multi-tenant, TCPA-compliant and backed by 586 hermetic tests, with a concurrency-safe dispatcher and warm-transfer routing. Built for high call volume at ~$0.10-0.15/min.

VapiFastAPICeleryNext.jsTelephony
Knowlyst RAG knowledge system import screen
LLM · RAG

Knowlyst

AI knowledge system that ingests web and video links, scrapes and stores the content, and answers user questions over it with RAG. Built at Viral Tech.

RAGScrapingVector DB
SignVision Urdu sign language translator
COMPUTER VISION

SignVision: Urdu Sign Language Translator

Real-time recognition via webcam: 1,662-dimensional MediaPipe Holistic keypoints classified by a CNN-LSTM, rendered as Urdu text and speech. Final year project.

MediaPipeCNN-LSTMTensorFlow
COMPUTER VISION

Fog Removal for Autonomous Vehicles

Visibility enhancement in foggy driving conditions: dark channel prior dehazing + CLAHE contrast, feeding YOLOv8 detection of pedestrians, vehicles and traffic signals.

YOLOv8OpenCVCLAHE
COMPUTER VISION

UK License Plate Recognition

Real-time vehicle license plate detection and number reading using YOLOv8, designed for traffic-signal monitoring applications.

YOLOv8OCRPython
Face recognition attendance system
COMPUTER VISION

Face Recognition Attendance System

Automated attendance with real-time facial recognition, Firebase integration, live video feedback and downloadable reports.

Face recognitionFirebaseOpenCV
VISION + NLP

Visual Question Answering

Deep learning system that interprets images and answers natural-language questions, combining computer vision and NLP techniques.

Deep learningNLPPyTorch
QUANT · BACKTESTING

Quant Strategy Validation Engine

Offline backtesting harness validating algorithmic trading strategies over ~9 years of BTC, ETH and SOL data, net of realistic fees and slippage. Enforced strict out-of-sample discipline (no-look-ahead, verified by tests), proved the strategies underperformed buy-and-hold, and found a risk overlay that cut max drawdown ~27%. Shipped 43 hermetic tests and a go/no-go report.

PythonBacktestingPandasRisk metrics
AI TOOL · LIVE

AI Resume Builder & Optimizer

AI resume builder that tailors a resume to a job description, scores ATS compatibility, and formats it to pass applicant tracking systems.

ReactOpenAI APINLPVercel
HR resume screening AI
AUTOMATION

HR Resume Screening AI

Recruitment automation that generates screening criteria from a job spec, pulls resumes via email, ranks candidates with AI matching, and sends bulk templated outreach.

OpenAI APIFlaskReactEmail automation
LLM · MULTI-MODEL

Multi-Model LLM System

Unified interface over GPT-4, Claude, Gemini and LLaMA with model comparison, switching and performance analytics for text, chat and code tasks.

GPT-4ClaudeGeminiFastAPIReact
MULTIMODAL · HEALTHCARE

AI Medical Chatbot

Multimodal medical assistant that analyzes medical images, answers health questions, and supports voice interaction using LLMs and computer vision.

LLaMA 3OpenAI APIComputer VisionSpeechFlask
COMPUTER VISION

Gesture-Based Calculator

Touchless calculator: an on-screen keypad operated by finger-pinch detection through a live webcam feed for real-time arithmetic.

MediaPipeOpenCVCVZonePython
LLM · NL-TO-SQL

Text-to-SQL with LLaMA 3

Streamlit app that turns natural-language questions into SQL with Groq's LLaMA 3, querying a live SQLite database and returning results in an intuitive UI.

LLaMA 3Groq APILangChainStreamlit
AUTOMATION · CONTENT

YouTube to Blog & Podcast

Pipeline that turns YouTube videos into blog posts and podcasts: fetches transcripts, summarizes with AI, generates audio, and ships to Drive and Sheets.

OpenAI APIyt-dlpGoogle APIsPython
AUTOMATION · CONTENT

AI-Generated Newsletter

Django system that generates location-specific, Axios-style newsletters with Claude, sourcing fresh articles via Perplexity and structuring them into HTML.

Claude APIPerplexity APIDjangoPython
COMPUTER VISION · MEDICAL

Plaque Segmentation

Medical-imaging system that segments arterial plaque in ultrasound images with YOLOv8, annotating regions with confidence scores for cardiovascular diagnostics.

YOLOv8PyTorchOpenCVPython
AUTOMATION · AGENTS

Instagram Agent

CrewAI multi-agent system that researches the market, plans content, generates visuals and writes captions to automate Instagram content end to end.

CrewAILangChainSerper APIPython