Skip to content
View rotask's full-sized avatar
1 follower · 3 following

Block or report rotask

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
rotask/README.md

Hi 👋, I'm Konstantinos Rotas

Typing SVG

📍 Athens, Greece  ·  AI Engineer @ Metlen Energy & Metals

👨‍💻 About Me:

AI-native engineer with an MSc in Applied Machine Learning from Imperial College London (Merit). Production experience deploying ML systems on Azure, AWS, and GCP across energy, education, and telecommunications. R&D focus on agentic workflows and LLM-based assistants. Master's thesis: Large Language Models for data compression.

🔭 Recent Experience:

  • Metlen Energy & Metals — AI Engineer (Apr 2025–present): Building clustering algorithms for energy profiling and annual consumption prediction for 500+ new smart-meter customers monthly, plus a look-alike pricing model in Azure ML for customers without historical data. Leading R&D on generative AI and agentic architectures.

  • Faculty AI (Department for Education): Authored ADRs and built FastAPI endpoints for the DfE Content Store assessment-data API on Azure; provisioned IaC with Terraform + Azure DevOps, cutting deployment time by ~15 hours per iteration. Built a Dash dashboard prototype demoed to EdTech developers at a sponsored hackathon.

  • Imperial College London — MSc Applied Machine Learning (Merit): Thesis on Large Language Models for data compression. Scholarship recipient (EUROTANKERS INC and Union of Greek Shipowners).

🚀 Currently Building:

  • Agentic workflows and LLM-based assistants — prototyping intelligent assistants and automated reasoning pipelines around LangChain, Google ADK, and Hugging Face Transformers.
  • Production ML on Azure ML — clustering and look-alike pricing for energy customers, with SQL + Python pipelines.

📫 Connect with me: LinkedIn

🛠️ Languages and Tools:

GenAI & LLMs

LangChain Hugging Face Google ADK Anthropic RAG

Machine Learning & Data Science

Python PyTorch TensorFlow scikit-learn NumPy Pandas MATLAB

Cloud, MLOps & Infrastructure

Azure AWS GCP Terraform Docker FastAPI GitHub Actions

Data & BI

PostgreSQL Oracle SQL Tableau Power BI

Other

Git Linux Bash

Pinned Loading

  1. LLMCompress LLMCompress Public

    LLM-Enhanced Text Compression: This project explores using Large Language Models (LLMs) to improve text compression efficiency. It evaluates various LLM architectures (GPT-2, Llama 2, Mistral-7B, Y…

    Python 1

  2. nlp-esg-extractor nlp-esg-extractor Public

    Rule-based vs LLM pipeline for extracting ESG KPIs (Scope 1 emissions, energy, water) from corporate sustainability PDFs. ClimateBERT + Docling + Claude / Gemini tool-use. F1 = 0.96 on 5 FY2025 rep…

    Python

  3. LiDAR-Object-Detection-CNN LiDAR-Object-Detection-CNN Public

    Forked from alexfrater/ASHLA

    LiDAR-based object classification system using CNN for autonomous robot navigation. Achieved 97% accuracy in classifying household objects with real-time operation. Developed at Imperial College Lo…

    Jupyter Notebook