AI/ML Engineer • Python Developer

Erim Cengiz

I build intelligent systems that connect machine learning, LLMs and production-ready Python backends.

Focused on RAG applications, applied machine learning and backend systems using Python, FastAPI, Django, PyTorch and modern AI tooling.

Open to AI/ML & Python opportunities

Istanbul, Türkiye • Open to relocation in Europe

TOOLS I BUILD WITH

  • Python
  • PyTorch
  • FastAPI
  • Django
  • LLM / RAG
  • Qdrant
erim@portfolio: ~

whoami

Erim Cengiz

focus

AI/ML · RAG · Python Backend

stack

Python · PyTorch · FastAPI · Django · Qdrant

status

Building intelligent systems

02 / SELECTED WORK

Featured projects

From document retrieval to predictive models — a selection of systems, experiments and the engineering behind them.

AI Engineering / RAG

RAG PDF Reader

A multi-service RAG application that turns PDFs into searchable context and generates answers grounded in retrieved document content.

PDF-to-answer pipeline
  1. PDF
  2. Chunking
  3. Embeddings
  4. Qdrant
  5. Retrieval
  6. LLM answer

Document ingestion → context-aware answers

  • Python
  • Django
  • Qdrant
  • LlamaIndex
  • Google GenAI
  • Docker
  • Inngest

NLP / Deep Learning

BERT Emotion Classification

A BERT-based text classifier built with PyTorch and Transformers to distinguish six emotion classes.

Six-class emotion model
  • Sad
  • Happy
  • Love
  • Angry
  • Fear
  • Surprise
Validation accuracy
≈69%
MCC
≈0.68

Reported validation results; there is room to improve classification quality.

  • Python
  • PyTorch
  • BERT
  • Transformers

Machine Learning / Regression

YouTube Channel Analytics

A regression workflow for predicting new subscribers from channel and video analytics, followed by ensemble and stacking experimentation.

R²
≈0.969
RMSE
≈76.1
MAE
≈27.0

Reported experiment metrics; later work explored ensembles and stacking.

  • Python
  • Pandas
  • Scikit-learn
  • Random Forest
  • CatBoost
  • XGBoost
  • LightGBM

Computer Vision / Robotics

Autonomous Vehicle / Object Detection

An autonomous-vehicle project combining visual object detection with stereo-camera-based distance estimation.

Object detection + distance estimation

  • YOLOv5
  • OpenCV
  • Python
  • Stereo Vision
  • ROS

Machine Learning / Anomaly Detection

Fraud Detection

A two-stage approach combining autoencoder representation/anomaly learning with a supervised Random Forest stage to identify fraud.

Minority-class recall
≈0.86

Recall describes detection of the minority class; it does not establish precision.

  • Python
  • Autoencoder
  • Random Forest
  • Scikit-learn

Deep Learning

Multi-output Neural Network

A TensorFlow / Keras network with three outputs: mutation flag, class label and disease risk. Experiments showed strong performance alongside signs of overfitting.

Three outputs · overfitting observed

Strong experimental results; generalisation needs further evaluation.

  • TensorFlow
  • Keras
  • Python

03 / EXPERIENCE

Engineering in practice

Team-based engineering and academic work connecting software with real systems.

  1. 2020–2021

    Engineering team

    Telemetry / Vehicle Control

    EVA TEAM

    Engineering experience with EVA TEAM, focused on telemetry and vehicle control.

    Technical contributionTelemetry and vehicle-control work within the team.

  2. Date to confirm

    Software engineering / academic project

    Autonomous vehicle academic project

    Institution to confirm

    Academic software engineering work combining object detection with stereo-camera-based distance estimation.

    Technical contributionVisual object detection and distance estimation using a Python, OpenCV, YOLOv5 and ROS stack.

    Role details to confirm

    View related project

04 / TECHNOLOGY

The tools behind the work

Python at the core, with a focus on applied machine learning, retrieval systems and backend development.

Data

Preparing, querying and working with data.

  • Pandas
  • NumPy
  • SQL
  • MongoDB

Computer Vision / Robotics

Visual perception and robotic systems.

  • OpenCV
  • YOLOv5
  • ROS

Development tools

Packaging, version control and development environments.

  • Docker
  • Git
  • Linux

05 / ABOUT

Building toward AI engineering

I'm a software engineering graduate focused on applied artificial intelligence, machine learning and Python systems.

My work spans RAG applications, NLP, computer vision, predictive modelling and backend development. I'm developing that foundation toward AI/ML engineering, with an interest in connecting useful models to well-structured software.

Education
Software Engineering BSc
Based in
Istanbul, Türkiye
Focus
AI/ML + Python
Mobility
Open to European relocation

06 / CONTACT

Let's build something intelligent.

I'm interested in AI/ML engineering, RAG, Python backend and applied machine-learning opportunities.

Open to AI/ML & Python opportunities

EMAIL

erimcengiz@hotmail.com

Send me an email