AI ENGINEER • LLM AGENTS • RAG

Shipping AI that real people use.

I'm Muzamil Rajper, an AI Engineer in Islamabad. I build LLM agents, RAG pipelines and FastAPI backends, and take them from prototype to production. Right now I'm building an AI coworker that works inside Slack for an Amazon marketing agency.

● Open to AI engineering roles
● ● ●
class Muzamil:
    focus = [
      "LLM Agents",
      "RAG Systems",
      "Evaluation",
      "Production AI"
    ]

    def build(self):
      return practical_ai

ABOUT

From psychology to AI engineering.

I studied psychology (BS, 3.87 CGPA) and trained as an engineer through the Microsoft / KAMK AI Developer program and Harvard CS50. I build end-to-end AI systems: agents with tool calling, RAG over documents and databases, APIs, evaluation and deployment.

My psychology background shows up in my research projects, where I test LLMs the way psychologists test people and decode brain signals with ML. I'm looking for AI engineering roles where I can ship real products with a strong team.

EXPERIENCE

Where I build today.

AI Engineer

Extreme Branding · Islamabad · Amazon marketing & PPC agency
Present
  • Built an AI coworker that works inside Slack: staff ask questions, upload files and get answers in the same thread, using recent channel and DM context.
  • Designed agentic tool calling for Asana: the assistant picks the best assignee, creates the task, follows up and reports back.
  • FastAPI backend with login, workspace-scoped data and 30 automated tests, plus a Next.js web app.
  • Kept AI costs low by routing across models (GPT-4o mini for quick replies, GPT-5 mini for analysis, Gemini as an option) with daily limits.
  • Rolled it out to testers in the company's Slack; now building an Amazon SP-API dashboard.
FastAPILLM AgentsTool CallingSlack APIAsana APINext.jsAmazon SP-API

TECHNICAL SKILLS

Tools I work with.

01

LLM Agents & RAG

LangGraph, LangChain, LangSmith, tool calling, ChromaDB, embeddings, OpenAI, Gemini, Groq, Ollama.

02

Backend & Deployment

Python, FastAPI, Flask, REST APIs, Docker, CI with GitHub Actions, Streamlit Cloud.

03

Machine Learning

Scikit-learn, TensorFlow, Keras, PyTorch (EEGNet), XGBoost, model evaluation and statistics.

04

Data

SQL, SQLite, MongoDB, Pandas, NumPy, sqlglot, data cleaning and analysis.

FEATURED PROJECTS

Things I've built.

03 • AGENTIC RAG

Agentic RAG Research Assistant

Upload PDFs or notes and ask questions. A LangGraph agent retrieves from ChromaDB, decides whether to use a calculator or web search, and answers with page sources. Runs locally on Qwen3 through Ollama, or on Groq in the cloud.

LangGraphChromaDBSentence TransformersOllamaGroqStreamlit
View Project on GitHub ↗
04 • LLM EVALUATION / COGNITIVE SCIENCE

Do Language Models Learn Like People?

LLMs act as participants in psychology experiments: a two-armed bandit and the Cognitive Reflection Test. I fitted Q-learning models to their choices and compared them with 44 human participants. qwen2.5:7b reached 0.90 accuracy on the human task design, but stuck to choices far more than people do.

OllamaQ-learningMaximum LikelihoodStatisticsCI
View Project on GitHub ↗
05 • DEEP LEARNING / BRAIN SIGNALS

Motor Imagery EEG Decoding

Decoding imagined left vs right hand movement from EEG across 104 people. EEGNet reached 68.3% on people it had never seen, against 61.9% for the classic CSP + LDA pipeline, with subject-level splits and significance tests.

PyTorchEEGNetCSP + LDAMNEStatistics
View Project on GitHub ↗
06 • MACHINE LEARNING / CYBERSECURITY

Network Security ML System

An end-to-end machine learning project for network security: data preprocessing, model training, evaluation, reusable ML artifacts and a FastAPI service in Docker.

PythonScikit-learnFastAPIDocker
View Project on GitHub ↗

Earlier ML projects

CERTIFICATIONS

Learning & foundations.

AI Developer Program — Microsoft, KAMK University & EU partners (ECTS)In progress
Google Data Analytics Professional CertificateData Analytics
IBM Data Science Professional CertificateData Science
Applied Data Science CapstoneApplied DS
CS50Computer Science Foundations

GET IN TOUCH

Hiring an AI engineer?

I'm open to AI engineer and junior roles, on-site in Islamabad or remote. I'd be glad to walk you through any of these projects.