Skip to content
View GorkaFS13's full-sized avatar

Block or report GorkaFS13

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
GorkaFS13/README.md

Hey, I'm Gorka

AI Student @ UPV/EHU · AI Agents · LLMs & MCP · Machine Learning

LinkedIn · Email · GitHub


About me

I'm a 4th-year Artificial Intelligence student at the University of the Basque Country (UPV/EHU).

I recently completed a 3-month internship building production AI agents: multi-agent systems with LangGraph, a computer-use desktop companion in Rust/Tauri, MCP integrations and systematic LLM evaluation.

I'm interested in building and understanding intelligent systems, especially combining different areas of AI such as deep learning, language models and optimization algorithms.

My main areas of interest are:

  • 🤖 AI Agents — multi-agent systems (LangGraph), MCP, computer use, tool design and evaluation
  • 🧠 Machine Learning & Deep Learning — model training, evaluation and comparison
  • 💬 Natural Language Processing — transformers, fine-tuning vs prompting
  • 👁️ Computer Vision — pose estimation and neural architectures
  • ⚙️ Optimization & Metaheuristics — heuristic search, genetic algorithms

Tech Stack

Languages

Python Rust TypeScript


AI Agents & Backend

LangGraph FastAPI Tauri Vue.js PostgreSQL Neo4j Docker


ML / DL Frameworks

PyTorch Transformers scikit-learn


Data & Notebooks

Jupyter NumPy Pandas Matplotlib


Tools

Git GitLab Jira VS Code Linux


Experience

AI Engineering Intern — Swap Energía (May–Aug 2026)

Worked on a production SaaS platform of AI agents (private codebase), across the full agent stack: reasoning, tools, memory and evaluation.

  • Multi-agent systems with LangGraph: routing, delegation, human-in-the-loop teams, 140+ automated evaluation cases
  • Computer-use desktop companion (Rust/Tauri): agents control Windows/Linux apps via accessibility APIs (AT-SPI, UIA/COM)
  • MCP integrations, secure credentials in agent skills, natural language → workflow compiler
  • Neo4j knowledge graph as agent memory; LLM observability with Phoenix

AI Agents LangGraph MCP Rust Tauri FastAPI Vue.js


Projects

Do LLM agents work in Basque? The same 30-task battery run in English, Spanish and Basque — measuring the agentic layer, not just knowledge.

  • Basque keeps its reasoning (100%) but loses the agentic layer: tool use drops to 25% without tools, and answers leak into other languages
  • New metric: language leaks — plus localized output contracts (ANSWER/RESPUESTA/ERANTZUNA) as a measured variable
  • Public leaderboard with failure gallery, n=3 runs with std, code-verified battery

AI Agents LLM Evaluation Basque Low-resource languages Tool use


Measured when agentic machinery actually pays off: the same 15-task battery solved three ways, on two models.

  • Direct prompting vs single tool-using agent vs multi-agent (LangGraph)
  • Without tools both models fail only SHA-256 — with tools, the $1/MTok model matches the $5/MTok one (15/15)
  • Native tool use, MCP server, automatic evaluation: accuracy, token cost and latency

AI Agents LangGraph MCP LLMs Evaluation


Built and compared different architectures for human pose estimation using the MPII dataset.

  • CNN (ResNet) vs Transformer (TokenPose)
  • Achieved 82% vs 48% accuracy
  • Full pipeline: preprocessing, training, evaluation and visualization
  • Analysis of spatial precision vs global context

Computer Vision Deep Learning Transformers PyTorch


Explored whether large language models can replace supervised training in classification tasks.

  • DistilBERT (fine-tuning) vs LLMs (Qwen, LLaMA)
  • ~97% accuracy vs <30% with prompting
  • Analysis of bias and limitations of generative models
  • Data augmentation experiments

NLP LLMs Transformers Prompt Engineering


Solved a graph optimization problem using different heuristic and metaheuristic approaches.

  • Implemented GRASP, Simulated Annealing and Genetic Algorithm
  • Genetic Algorithm achieved Q ≈ 0.89
  • Compared solution quality, time and stability
  • Trade-off analysis: exploration vs exploitation

Optimization Metaheuristics Genetic Algorithm Graph Theory


Currently learning

  • Designing and evaluating agent systems in production
  • Rust for systems-level and desktop development
  • Deeper understanding of optimization techniques

Let's connect

I'm always open to collaborations, part-time roles and interesting conversations about AI.

email: gorkafernandez47@gmail.com


Gorka's GitHub Stats

Pinned Loading

  1. agent-architectures-comparison agent-architectures-comparison Public

    Prompting vs single agent vs multi-agent (LangGraph), measured on the same task battery

    Python 1

  2. human-pose-estimation-deep-learning human-pose-estimation-deep-learning Public

    Comparative study of CNN vs Transformer architectures for human pose estimation.

    Jupyter Notebook 1

  3. nlp-classification-finetuning-vs-prompting nlp-classification-finetuning-vs-prompting Public

    Comparative study of fine-tuning vs prompting for text classification using Transformer and LLM models.

    Jupyter Notebook 1

  4. community-detection-metaheuristics community-detection-metaheuristics Public

    Comparative study of heuristic and metaheuristic algorithms for community detection in graphs.

    Jupyter Notebook 1

  5. euskal-agent-bench euskal-agent-bench Public

    Do LLM agents work in Basque? An agentic benchmark across English, Spanish and Basque

    Python 1