Anastasios Stamoulakatos

Anastasios Stamoulakatos

Data Scientist at Satalia | PhD in Applied AI

Sitemap

A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.

Pages

Posts

Agentic Data Guardian: Enterprise Data Quality Management

less than 1 minute read

Published:

Designed and built AI multi-agent workflows to automate the detection and remediation of data quality anomalies in enterprise databases. Implemented Google ADK and AutoGen agents that continuously validate and update schemas, keeping model answers grounded and reducing hallucinations.

Creative AI: Evaluating and Ranking AI Creativity

less than 1 minute read

Published:

Researched multi-agent collaboration strategies and LLM-as-a-judge paradigms to evaluate and rank creative outputs. Benchmarked agent architectures (CrewAI, AutoGen, LangGraph) on creative marketing tasks.

Strava Activity to Google Sheets Sync

less than 1 minute read

Published:

Automation project to sync Strava training/activity logs directly into Google Sheets using the Strava API and Google Sheets API. Implemented automated OAuth token rotation and scheduled cron-like syncing.

Unlocking the Power of Multimodal Embeddings: A Hands-on Guide

less than 1 minute read

Published:

Multimodal embeddings allow us to represent diverse data types—such as text, images, audio, and geospatial coordinates—within a shared vector space, enabling advanced semantic search and cross-modal reasoning.

Retrieval-Augmented Generation (RAG) 101

less than 1 minute read

Published:

Retrieval-Augmented Generation (RAG) bridges the gap between static LLM parameters and dynamic external data. In this guide, I break down the core components of a RAG pipeline—from document chunking and vector embeddings to context retrieval and generation—and explain how real-time tools like Web Search integration keep model answers accurate and grounded.

Agentic Frameworks: A Comparison

less than 1 minute read

Published:

Selecting the right framework is crucial when moving from prototype agents to production. This article compares popular agentic development frameworks (such as CrewAI, AutoGen, and LangGraph), analyzing their design philosophies, state management capabilities, and developer ergonomics.

Building Effective AI Agents: A Brief Guide and Best Practices

less than 1 minute read

Published:

AI agents are redefining how we automate workflows. Building reliable agents requires more than just calling an LLM in a loop; it demands robust architectures for task planning, execution monitoring, tool access (like web search), and evaluation.

Check out my Blog on Medium

less than 1 minute read

Published:

I regularly write about Data Science, AI, and my experiences in the industry on Medium.

applied_research

PyTorch IBN-Encoder LSTM-Decoder

Published:

  • Encoder-Decoder network architecture combining IBN-Net feature extraction with LSTM sequential modeling.
  • Designed for video frame-level prediction, subsea survey annotations, and sequential data analysis.
  • Developed during PhD studies to automate pipeline anomaly detection over continuous video frames.

PyTorch Swapping Autoencoder

Published:

  • Implementation of Swapping Autoencoders for deep generative representation learning.
  • Enables texture and structure manipulation for image-to-image translation tasks.
  • Part of PhD research on unsupervised representation learning.

PyTorch Video Dataset Loader & Sampler

Published:

  • Efficient dataset loader and sampler helper classes for video classification tasks in PyTorch.
  • Optimizes random sampling, clip loading, and preprocessing routines for heavy video data pipelines.
  • Used extensively during PhD projects to accelerate model training on subsea survey footage.

Custom Cutout Data Augmentation in PyTorch

Published:

  • Implementation of Cutout data regularization/augmentation for convolutional neural networks in PyTorch.
  • Provides modular and flexible cutout masks to improve model generalization and robustness against occlusion.
  • Developed during PhD studies to enhance data variety for pipeline inspection datasets.

PyTorch 3D IBN-Net

Published:

  • 3D Convolutional Neural Network (3D CNN) incorporating Instance-Batch Normalization (IBN-Net) blocks.
  • Designed for video spatiotemporal analysis and action recognition with enhanced domain generalization.
  • Developed during PhD studies to improve feature extraction robustness under varying subsea conditions.

Panoptic Segmentation with Mask2Former & PyTorch Lightning

Published:

  • Training, evaluating, and running inference for Panoptic Segmentation models using Mask2Former.
  • Leveraging PyTorch Lightning and Hugging Face Transformers for modular and scalable training pipelines.
  • Built during Track32 AI research and development.

WPP Open ResearchLab: Data Quality Assurance Agent

Published:

  • Research and development of an intelligent AI agent for automated data quality assurance and schema validation.
  • Implementing reasoning-based agents to analyze databases, identify anomalies, and enforce consistency constraints.
  • Part of the WPP Open ResearchLab initiative.

cv

publications

A Comparison of the Performance of 2D and 3D Convolutional Neural Networks for Subsea Survey Video Classification

Published in IEEE OCEANS 2021, 2021

Conference paper comparing 2D and 3D CNN architectures for temporal and spatial modeling of underwater pipeline inspection videos.

Recommended citation: Stamoulakatos, A., & Tachtatzis, C. (2021). A Comparison of the Performance of 2D and 3D Convolutional Neural Networks for Subsea Survey Video Classification. In OCEANS 2021 (pp. 1-6). IEEE. https://ieeexplore.ieee.org/document/9706125

talks

teaching

C++ Teaching Assistant

Undergraduate Course, University of Strathclyde, EEE Department, 2018

  • Assisted 2nd year students in C++ lab exercises and final project
  • Taught fundamentals of coding and object oriented programming

Building Your First AI Agent

Educational Repository, GitHub Tutorial / Open Source, 2025

  • A beginner-friendly tutorial and code template for building autonomous AI agents.
  • Covers agent loop design, tool calling, and prompt engineering fundamentals.

Introduction to AI Agents

Guest Lecture, Athens University of Economics and Business (AUEB), 2026

  • Guest lecture on the architecture and development of AI agents.
  • Provided practical code examples and hands-on exercises for students.