Implement and test prompt engineering strategies, RAG (Retrieval-Augmented Generation) and model integration in prototype and production environments.
Build and evolve AI agents based on LLMs for automated customer service in chatbots.
Develop, train and evaluate text classification models for intent recognition and other NLP use cases.
Create data pipelines for preparing, cleaning, balancing and enriching textual datasets.
Define and monitor performance metrics, performing statistical analyses for continuous model improvement.
Collaborate with Product, Engineering and Data Science teams to translate business needs into applied AI solutions.

Degree in Statistics, Data Science, Computer Science or related fields.
Programming in Python and experience with libraries such as Pandas, Scikit-learn, Transformers and visualization tools (Matplotlib, Seaborn, Plotly).
Knowledge of applied statistics and exploratory data analysis, including hypothesis testing, classification metrics and model validation.
Experience training and evaluating classical classification models (logistic regression, tree-based models, etc.).
Knowledge of NLP, with focus on BERT and semantic representation techniques such as embeddings.
Experience with LLMs, prompt engineering, AI agents and using RAG architectures in customer-service chatbots.
Practical experience applying AI to products and automating conversational flows.

Flexible Benefit (you choose how to use it according to your needs: culture, ride-hailing app, subscriptions, gym, food, etc.); 🎉🚗💼🏋️🍔
Unipart Unimed Health Plan; 🏥
Career development path; 🚀
Hybrid work; 🏡
Day Off; 🌞
Short Friday; 😎
Collaborative and dynamic work environment. 🤝💼

Mid-level Data Scientist

Key skills