Avatar

Francisco Rodriguez, Ph.D.
Senior Data Scientist · NLP Researcher

About

Hi! 👋 I’m a senior data scientist and NLP/LLM researcher based in Valais, Switzerland. Over the past nine years, I’ve worked at the intersection of academia and industry, building machine learning systems end to end. My main focus is on large language models — from data preparation and fine-tuning to evaluation and deployment in production. Along the way, I’ve worked on retrieval-augmented generation, predictive analytics, and customer intelligence.

What I do best

  • NLP & LLMs: adapting models to specific domains, evaluating systems, and exploring safety and bias
  • Production ML: building reliable data pipelines, setting up CI/CD for models, feature stores, monitoring, and A/B testing
  • Analytics that drive impact: translating raw feedback, support tickets, or chats into clear insights and decisions

Current work

At Hilti AG, I focus on customer feedback intelligence, retention modeling, and building scalable ML pipelines that power analytics and operational tools.

I also collaborate with UNED’s NLP group on projects around bias mitigation, multilingual sexism detection, and LLM fine-tuning. I co-led the EXIST shared task and created the MeTwo dataset.

Interests

  • NLP & LLMs (fine-tuning, RAG, RLHF)
  • Predictive Analytics
  • Customer Experience Intelligence
  • Information Retrieval
  • Bias & Fairness in AI
  • Scalable ML/MLOps (AWS, GCP, Spark)

Education

  • PhD in Natural Language Processing (summa cum laude), 2025

    UNED

  • MSc in Machine Learning and Natural Language Processing, 2019

    UNED

  • MSc in Telecommunications Engineering, 2016

    UPCT

  • BSc in Telecommunications Engineering, 2014

    UPCT

Recent Publications

For a comprehensive list, please refer to my Google Scholar profile .

Leveraging Unsupervised Task Adaptation and Semi-Supervised Learning With Semantic-Enriched Representations for Online Sexism Detection

Over the past decade, the proliferation of hateful and sexist content targeting women on social media has become a concerning issue, …

Detecting sexism in social media: an empirical analysis of linguistic patterns and strategies

With the rise of social networks, there has been a marked increase in offensive content targeting women, ranging from overt acts of …

Automatic Classification of Sexism in Social Networks: An Empirical Study on Twitter Data

During the last decade, hateful and sexist content towards women is being increasingly spread on social networks. The exposure to …

Get in touch

Quick note or collaboration idea? Send me a message.

Email: franct14@gmail.com
Location: Valais (Wallis), Switzerland

LinkedIn · GitHub · Google Scholar