This is a fully remote position, open to applicants in Brazil.

📋 Description

• Design and implement assessments and tests for synthetic personas to simulate various user profiles, goals, and behaviors.

• Develop experimental pipelines for LLM-as-a-Judge, including the construction of prompts, rubrics, and automated evaluation protocols for scalable analysis of responses generated by AI models, integrating concepts from Reinforcement Learning and Preference Optimization.

• Investigate and apply preference optimization techniques and reinforcement learning for the continuous improvement of language models, assessing impacts on quality, robustness, and alignment.

⛳️ Requirements

• Education: PhD.

• Fields of Study: Computer Science, Computer Engineering, Information Systems, Data Science, Statistics, Applied Mathematics, or related areas in Computing, Artificial Intelligence, and Machine Learning.

• Proficiency in Python programming.

• Understanding of Machine Learning and Deep Learning fundamentals.

• Familiarity with Large Language Models (LLMs) and Generative AI.

• Experience with AI model development libraries (PyTorch and/or Hugging Face Transformers).

• Ability to read and comprehend scientific articles in English.

• Basic knowledge of experimentation, result analysis, and model evaluation.