🎯 ACTIVELY SEEKING WERKSTUDENT OPPORTUNITIES • 20H/WEEK AVAILABLE

Hi, I'm Edgar Abasov

AI Engineer × Multi-Agent Systems × RAG Specialist

Master's student at HAW Kiel with 2+ years production experience.
Building intelligent systems with LangGraph, FastAPI, and Docker.

Greifswald / Berlin, Germany German B2 | English C1
2+ Years Production Experience
20 Hours/Week Available
15% Chatbot Accuracy Improvement

Why Hire Me?

Edgar Abasov - AI Engineer
Available Immediately
Work Authorization: Student Visa

🎯 Perfect Fit for Your Team

I'm a Master's student in Data Science at HAW Kiel with 2+ years of production AI experience. I bring a unique combination of academic excellence and real-world engineering skills.

Production-Ready AI

Built and deployed chatbots at Bank of Georgia, improving accuracy by 15% using modern NLU and RAG techniques.

Multi-Agent Systems Expert

Currently building unimate - a LangGraph-based multi-agent system for German exam preparation with RAG architecture.

DevOps & Cloud Native

Experienced with Docker, FastAPI, AWS (SageMaker, S3, EC2), and CI/CD pipelines for scalable ML deployments.

Multilingual & Multicultural

German B2 (speaking), English C1. Experience working in international teams across Georgia, Poland, and Germany.

📊 Quick Facts

  • Available for 20 hours/week (Werkstudent)
  • Flexible for hybrid work in Greifswald/Berlin
  • Expected graduation: February 2026
  • AWS ML Specialty certification in progress

Production Experience

I've shipped real AI products that serve thousands of users daily

Oct 2023 - Sep 2024

AI Engineer

Bank of Georgia • Production Environment

15% Accuracy Improvement
1000s Daily Users
  • Improved chatbot accuracy by 15% using advanced NLU models and conversation design
  • Built bilingual (Georgian/English) features with full DevOps pipeline
  • Deployed production services using Docker, MongoDB, and PostgreSQL
  • Worked in Agile environment with Jira and CI/CD workflows
Languages: Python SQL Bash AI/ML: LLM NLU RAG DevOps: Docker MongoDB PostgreSQL
Mar 2021 - Mar 2022

Data Scientist

Batumi Shota Rustaveli State University • Research Project

0.77 Model Accuracy
Web App Delivered
  • Developed speech-to-text web application with 77% accuracy for client use
  • Researched audio processing using Spectrograms and Fast Fourier Transform
  • Implemented end-to-end ML pipeline from data collection to deployment
Python Kaldi Librosa Speech Recognition Signal Processing
2021 - 2024

Python Instructor

Freelance • Teaching & Mentoring

80+ Students Taught
12-14 Age Group
  • Taught Python programming to 80+ students in online classes
  • Developed innovative teaching methods for complex programming concepts
  • Created game-based learning projects using Pygame
Python OOP Data Structures Pygame Git

Tech Stack 2026

Production-ready skills in modern AI/ML technologies

Languages & Frameworks

Python
95%
SQL/NoSQL
85%
Bash/Linux
75%

Machine Learning

PyTorch
80%
Scikit-learn
90%
LLMs & NLP
85%

Cloud & DevOps

AWS (SageMaker, S3, EC2)
70%
Docker & CI/CD
80%
MongoDB & PostgreSQL
80%

Languages & Soft Skills

🇩🇪

German

B2 (Speaking)

B2
🇬🇧

English

C1 (Professional)

C1

📜 Certifications & Learning

AWS ML Specialty

In Progress - Feb 2025

Azure Data Scientist

Completed - 2021

Mathematics for ML

Specialization - 2025

Live Projects

Production-ready AI systems you can try right now

🟢 Live Demo ⭐ 12

CoverBot - RAG Document Chatbot

Production-ready RAG chatbot using Gemini API for intelligent document Q&A. Demonstrates real-world implementation of retrieval-augmented generation.

Python Gemini API Streamlit RAG Vector DB
< 2s response time
10MB+ documents
🟢 Dockerized ⭐ 8

Diamond Price Prediction API

Scalable ML API with 90% accuracy using XGBoost. Fully containerized with Docker for easy deployment. Production-ready with proper error handling and logging.

FastAPI Docker XGBoost Flask CI/CD
90% accuracy
< 100ms latency
🟢 API Ready ⭐ 6

PneuNet - Medical Image Classification

PyTorch CNN for pneumonia detection served via FastAPI. Production-ready endpoints with proper validation and Docker deployment.

PyTorch FastAPI Docker CNN Medical AI
94% accuracy
HIPAA compliant
✅ Completed

Customer Churn Prediction

ML model achieving 85% accuracy in predicting telecom customer churn. Includes comprehensive EDA and feature engineering.

Scikit-learn Random Forest EDA Feature Engineering
✅ Award Winner

Stamo.AI - Text to Video

MediaLab 5K Lari Winner (2024). Converts blog content to animated videos using Stable Diffusion and NLP.

Stable Diffusion NLP Browser Extension
✅ Research

Fine-tuning NER with BERT

Named Entity Recognition model fine-tuned on CoNLL-2003 dataset using BERT and PyTorch. Demonstrates advanced NLP capabilities.

PyTorch BERT NER Transformers
20+ Repositories
50+ Stars
100+ Commits/Year
View All Projects on GitHub

Academic Excellence

Current

Master of Science - Data Science

HAW Kiel, Germany

Feb 2024 - Feb 2026 (Expected)

Machine Learning Cloud Computing Data Visualization Multivariate Calculus
Erasmus+ Exchange Student

Bachelor of Science - Computer Science

Shota Rustaveli State University, Georgia

2019 - 2024

Software Engineering Algorithms Databases OOP
Erasmus+ Exchange at Silesian University, Poland (2022)

Ready to Join Your Team

Looking for a Werkstudent (20h/week) or internship position in AI Engineering / Data Engineering.
Available for hybrid work in Greifswald/Berlin area.

Immediate Availability
Valid Work Permit
German B2 Speaker
Schedule an Interview

Let's Connect

I respond within 24 hours • Available for video calls

Quick Contact

Location

Greifswald / Berlin, Germany

Availability

  • Available immediately
  • 20 hours/week (Werkstudent)
  • Hybrid work preferred
  • Until Feb 2026 (graduation)

Send a Message