AI Engineer · Rawalpindi / Islamabad, Pakistan · Open to Work

Muhammad
Saif Ur
Rehman

I build intelligent systems - RAG pipelines, multi-agent orchestration, voice AI, and no-code automation. End-to-end. Actually ships.

Available for AI Engineering roles & Freelance · Remote OK
$ saif --stack
→ LLMs · RAG · CrewAI · LangChain · AWS · Vapi · Retell · n8n
2,000+
Hours Building AI
3
Production Deployments
10+
Automation Workflows
6+
Certifications
SCROLL
── · ──────────────────────────── · ──
01

About Me

I'm an AI Engineer and BS AI graduate from COMSATS University Islamabad, passionate about building systems that work in the real world, not just in notebooks.

My core expertise spans end-to-end AI pipelines: fine-tuning open-source LLMs, building RAG-based production systems on AWS, and orchestrating multi-agent workflows with CrewAI.

I'm currently deep into voice AI agents (Vapi & Retell) and n8n automation, integrating AI into real business workflows. The goal: make AI actually useful for people who aren't engineers.

When I'm not coding, you'll find me studying how frontier AI systems are architected and figuring out how to build the next generation of them. Outside of AI, I'm into gaming, fitness, and cycling.

RAG ArchitecturesMulti-Agent Systems Voice AI · Vapi · Retelln8n Automation LLM Fine-TuningComputer Vision AWS DeploymentCrewAI · LangChain
🏅
IBM Generative AI Engineering Professional ↗
IBM · Professional Certificate
🤖
📊
Google Data Analytics ↗
Google · Coursera
🎓
Innoquest Cohort 1, AI Training
Innovista Rawal
💼
Microsoft Office Specialist
Excel · Word · PowerPoint
── · ──────────────────────────── · ──
02

What I Build

🧠
RAG & LLM Systems

End-to-end retrieval-augmented generation pipelines covering document ingestion, vector indexing, LLM integration, and cloud deployment. Built to be accurate and production-ready.

LangChainPineconeOpenAIAWS
🤖
Multi-Agent AI Systems

Autonomous agent pipelines using CrewAI and LangGraph. Research, analyst, and writer agents working in concert to automate complex multi-step cognitive tasks.

CrewAILangGraphPython
🎙️
Voice AI Agents

Intelligent voice agents via Vapi and Retell for customer service, booking, and lead qualification. Natural conversations with LLM reasoning behind every response.

VapiRetell AICustom LLM
⚙️
n8n AI Automations

Visual AI workflow automation with n8n for CRM integrations, email AI, document processing, and lead nurturing, all triggered by real business events.

n8nWebhooksOpenAI API
👁️
Computer Vision

Custom CV models for detection, segmentation, and classification using YOLOv8 and PyTorch. From custom dataset training to real-time video inference.

YOLOv8PyTorchOpenCV
🔧
LLM Fine-Tuning

Adapt open-source models to your domain using LoRA/PEFT via HuggingFace. Efficient fine-tuning on custom datasets without needing a massive GPU cluster.

HuggingFaceLoRA/PEFTSageMaker
── · ──────────────────────────── · ──
03

My Journey

2022
Started AI Engineering
COMSATS University Islamabad
Began BS in AI (CGPA: 3.4 / 4.0), diving deep into ML foundations, linear algebra, and Python from day one.
2024
First Production RAG System
Innoquest Cohort 1 · End-to-End Medical Chatbot
Built and deployed a full RAG pipeline on AWS EC2 + SageMaker with Pinecone vector search as the capstone of Innoquest. First real cloud deployment.
2024
IBM GenAI Professional Certificate
IBM · Coursera
Rigorous certification covering LLM internals, fine-tuning patterns, and production GenAI deployment best practices.
2025
AI Intern - NCAI
Medical Imaging Lab · COMSATS Islamabad
6-month internship fine-tuning LLMs, building RAG systems and conversational AI. Also worked on fine-tuning VLMs and Swin Transformers on medical imaging data.
2024
Innoquest Cohort 1 Graduate
Innovista Rawal · AI Training Program
Intensive AI bootcamp: applied ML, industry problem-solving, and shipping systems beyond academic exercises.
2025
FYP: Fluxwell
AI-Powered Lifestyle Advisor
Full-stack AI application featuring real-time posture detection with voice feedback, agentic RAG for personalized guidance with action capabilities like nutrition plans and workout generation, community blogs with reactions, and health metrics tracking with real-time anomaly alerts.
2025
Agentic AI & Multi-Agent Systems
CrewAI · LangGraph
Learned and applied agentic AI architectures during and after my FYP. Built multi-agent pipelines that research, analyze, and write autonomously. Pivoted focus toward agentic systems.
2026 →
Voice AI & n8n Automations
Vapi · Retell · n8n
Building intelligent voice agents and AI-powered business automation workflows, bridging LLMs with real-world systems. Currently shipping.
── · ──────────────────────────── · ──
04

Projects

⭐ Featured · FYP
Fluxwell — AI Lifestyle Advisor

Co-led development as project leader in a 2-person team. Built a health and lifestyle advisor around 7 autonomous AI agents, each owning a distinct domain: personalised workout planning, adaptive meal planning, multimodal RAG coaching, real-time vitals monitoring with anomaly alerts, live posture analysis with voice guidance, and AI-driven blog generation. Includes a progress dashboard with visual charts and gamification (badges, streaks).

React.jsFastAPIMongoDBPineconeGroqLangChainLangGraph
// key features
Real-time Posture Detection
+
Voice Feedback System
+
Agentic RAG Guidance
+
Nutrition & Workout Plans
+
Community Blogs & Reactions
+
Metrics Tracking & Anomaly Alerts
⭐ Featured Project
End-to-End Medical Chatbot

Production-deployed RAG medical chatbot on AWS. Ingests medical knowledge bases into Pinecone, retrieves context per query, and augments LLM responses for accurate, grounded medical answers. Full pipeline from HuggingFace embeddings to SageMaker endpoint.

PythonLangChainPineconeHuggingFaceAWS EC2SageMakerRAG
// system architecture
User Query Input
HuggingFace Embeddings
Pinecone Similarity Search
LangChain Context Injection
AWS SageMaker LLM Endpoint
Grounded Medical Response ✓
🤖 Multi-Agent
Market Research Crew

Multi-agent CrewAI system that autonomously validates business ideas. A researcher gathers market data, an analyst evaluates viability, and a writer produces a comprehensive investment report with zero human intervention.

PythonCrewAIOpenAIMulti-Agent
🤖 Multi-Agent
Research & Blog Writing Agent

Dual-agent CrewAI pipeline where a research agent deep-dives any topic, passing structured findings to a writing agent producing publication-quality blog posts. Clean agent handoff and task decomposition.

PythonCrewAIAgent Orchestration
🎯 Computer Vision
Pothole Image Segmentation

YOLOv8 semantic segmentation model detecting and delineating potholes in real-time video. Trained on custom dataset with production-ready inference pipeline for smart city applications.

YOLOv8PyTorchOpenCVReal-time
🔥 LLM Fine-Tuning
Open-Source Model Fine-Tuning

Parameter-efficient fine-tuning of open-source LLMs using LoRA/PEFT. Adapts foundation models to domain-specific tasks efficiently without needing a massive compute budget.

HuggingFaceLoRA/PEFTPyTorchTransformers
👁️ Computer Vision
Hand Gesture Recognition

Real-time gesture classifier recognizing multiple hand gesture classes from live camera input. Shows ML training, custom dataset pipelines, and live inference, applicable to HCI and accessibility.

PythonTensorFlowOpenCVReal-time
💼 Freelance · Client Project
Alzheimer’s Detection App

Built a full-stack Alzheimer’s detection application as a freelance project. Trained LeNet, VGG16, MobileNetV2, ResNet, and a custom architecture on an Alzheimer’s dataset. The custom model outperformed all benchmarks and was integrated into the final product. Built Flask backend + React frontend with real-time inference.

PythonFlaskReactPyTorchCNNMobileNetV2ResNetCustom Model
Private · Available on request
// model pipeline
Alzheimer’s Dataset
Multi-Architecture Training
Custom Model Selection
Flask API Backend
React Frontend + Real-time Inference ✓
🎙️ Voice AI
AI Voice Follow-Up Agent

Built an n8n + Vapi workflow that reads a Google Sheet of sales contacts, automatically calls clients with no follow-up logged, and after each call has the AI agent summarize the conversation, update the Follow-Up Summary, and mark the contact as followed up. Eliminates manual tracking overhead for sales teams.

n8nVapiVoice AIGoogle SheetsAutomation
Available on request
⚙️ n8n Automation
Customer Support Workflow

Built an n8n automation that manages customer support entirely through Gmail. Processes incoming messages, resolves queries automatically, and for defective item cases generates a unique RMA return number sent back to the customer.

n8nGmailRMA AutomationWebhooks
Available on request
🧠 RAG
RAG Pipeline (n8n)

Website-embeddable RAG chatbot that retrieves from company documents stored in Pinecone and generates accurate context-aware responses to FAQs and business queries. Plug-and-play for any business website.

n8nPineconeRAGOpenAI APIEmbeddings
Available on request
── · ──────────────────────────── · ──
05

Recognition

// verified experience
"Completed a 6-month AI internship at NCAI Medical Imaging Lab, contributing to fine-tuning VLMs and Swin Transformers on medical imaging data."
— NCAI · National Centre of Artificial Intelligence, COMSATS Islamabad
"Innoquest Cohort 1 Graduate — selected for intensive AI training focused on applied ML and shipping production systems beyond academic exercises."
— Innovista Rawal · AI Training Program
── · ──────────────────────────── · ──
06

Skills & Stack

LLMs & GenAI
LangChain / LangGraph
OpenAI SDK / API
HuggingFace Transformers
Fine-Tuning (LoRA / PEFT)
Amazon Bedrock
RAG Architecture Design
Prompt Engineering
Agents & Automation
CrewAI
n8n Workflows
Vapi Voice AI
Retell AI
Multi-Agent Orchestration
Tool Use / Function Calling
API Integration
Cloud & Infra
AWS EC2 / S3
Amazon SageMaker
Pinecone Vector DB
Qdrant / FAISS
MongoDB
Git / DVC / Git LFS
MLOps
Docker
MLflow
DVC
Jenkins
CircleCI
GitHub Actions
ML & Vision
PyTorch
TensorFlow / Keras
Scikit-learn
YOLOv8 Segmentation
OpenCV
NLP
Text Classification
Sentiment Analysis
RNN / LSTM
Fine-Tuning
RAG
Languages & Tools
Python (Primary)
Jupyter / Colab / Kaggle
REST APIs
Pandas / NumPy
Matplotlib / Seaborn
FastAPI (basics)
── · ──────────────────────────── · ──
07

Let's Build Together

Open to opportunities.

Looking for AI Engineering roles, freelance automation projects, and collaborations on agentic or voice AI. Based in Islamabad, open to remote worldwide.

Send a Message
SAIF.AI · Portfolio Assistant
SAIF.AI
Hi! I know everything about Muhammad Saif Ur Rehman's background, projects, and skills. Ask me anything!