Muhammad
Raad
Shaukat
I built an AI agent now driving customer engagement and revenue for European business owners. I engineered a Vision RAG system that holds 25 years of institutional knowledge for a mineral mining company, turning decades of data into instant, actionable answers. This is what I build. Let's build yours next.
Model Training · Model Finetuning · Agentic AI · RAG · FastAPI
Career in Numbers
Track Record
Production AI systems across two engineering firms
From RAG pipelines to autonomous booking agents
Multilingual sentiment across English, Arabic, and Urdu
Vision-RAG over a 300+ document mining report corpus
Selected Work
Projects
Conversational Cross-Channel Booking Agent
A cross-channel booking agent built on LangGraph with stateful conversation context. Integrates WhatsApp, Instagram, Gmail, and Outlook into a single inbox. Orchestrates calendar syncing across Google and Microsoft calendars via OAuth flows. Sustains 99%+ uptime, cutting vendor scheduling overhead by roughly 1.5 hours daily and saving up to 8.5 hours per week.
Vision-RAG Mining Intelligence System
End-to-end RAG pipeline using Gemini 2.5 Flash multimodal capabilities to parse 300 DPI scanned mining reports and reconstruct tables where traditional OCR failed. FAISS dense embeddings combined with BM25 sparse search via Reciprocal Rank Fusion — 93%+ accuracy on a 300+ document corpus with sub-3s latency.
Early Retirement — AI-Driven NPC Game
NPCs that respond to what you actually said instead of cycling through a dialogue tree. SmolLM2-360M, fine-tuned with QLoRA on 20,182 synthetic dialogues, running locally at ~17 MB. Full voice loop — speech in, model, speech out — at roughly 3 seconds end to end.
Multilingual Sentiment Analysis Pipeline
Sentiment classification across English, Arabic — Modern Standard and Saudi dialect — and Urdu. Custom attention heads on AraBERT and RoBERTa-large recover morphology a general multilingual model misses. Trained on 120K+ labeled reviews, ablated against standard fine-tuning to isolate the gain. 96% F1 across all three, 14 points above off-the-shelf on Saudi dialect Arabic, serving live inference under 1s per review.
Capabilities
Skills
Generative AI & LLMs
Machine Learning
Backend & Infrastructure
Cloud & APIs