Skip to content
View parlatellioglu's full-sized avatar

Highlights

  • Pro

Block or report parlatellioglu

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
parlatellioglu/README.md

Parla Tellioglu

Computer Science / Software Engineering MEng — University of Birmingham

Website LinkedIn Email


I design and build software and intelligent systems, spanning engineering, data, and applied AI.

Currently

  • Software Engineer Intern — Simsoft Computer Technologies. Building a local-LLM knowledge and compliance assistant with retrieval-augmented generation, plus document-validation and process-compliance workflows.
  • Data Science Intern — Doğuş Teknoloji. Working on LLM-based quality-assurance automation and ARIMA time-series forecasting for strategic projections.
  • Tutoring university students in Python on the side.

Selected projects

Project What it is
Pulse Offline, LLM-orchestrated penetration-testing pipeline. A LangGraph state machine coordinates 12 security tools (nmap, sqlmap, and others) with local Ollama models and streams its reasoning to the UI in real time. Next.js + FastAPI. 1st place — BirmingHack 2.0.
SocratEase AI communication coach for public speaking. Combines speech analysis, computer-vision-based eye-contact and expression tracking, and multimodal models to assess fluency and coherence. 1st place — BirmingHack 1.0.
Camera-Calibration Toolkit for calibrating cameras and removing lens distortion with OpenCV and a printed checkerboard target. Supports pinhole and fisheye models.
ARIMA-Forecasting End-to-end Box–Jenkins ARIMA workflow for annual time-series forecasting: exploratory analysis, stationarity testing, model selection, residual diagnostics, and one-step-ahead forecasting.
ISE-config-prediction Comparative evaluation of ML regression models on software-configuration data, with statistical verification of the results.

Background

  • Computer vision research at METU's Applied Intelligence Research Lab — OpenCV pipelines for color filtering, homography estimation, foreground/background separation, and pose estimation.
  • Two-time BirmingHack winner (Best Use of AI Agents on Arm, 2026; Best AI Hack, 2025).

Skills

My Skills

  • Programming — Python, Java, C
  • AI / ML — LLMs, LangGraph, Ollama, XGBoost
  • Data Science — ARIMA, Time Series, Statsmodels
  • Computer Vision — OpenCV, NumPy
  • Web & Tools — Next.js, FastAPI, Flask, Git

Pinned Loading

  1. siddharth-shringarpure/SocratEase siddharth-shringarpure/SocratEase Public

    SocratEase: Speak smarter with AI-powered feedback.

    Jupyter Notebook 5

  2. 4dw1tz/Pulse 4dw1tz/Pulse Public

    TypeScript

  3. Camera-Calibration Camera-Calibration Public

    A practical toolkit for calibrating cameras and removing lens distortion using OpenCV and a printed checkerboard target. It covers both the standard pinhole camera model and the fisheye model, and …

    Jupyter Notebook 1

  4. ARIMA-Forecasting ARIMA-Forecasting Public

    End-to-end Box–Jenkins ARIMA workflow for annual time-series forecasting, covering exploratory analysis, stationarity testing, model selection, residual diagnostics, and one-step-ahead forecasting …

    Jupyter Notebook 1