PhD Research Fellow – Agents, Monitoring, AI Reliability, Model Evaluation

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

📋 Description

• Create execution flow maps for agents, pinpointing essential areas for log collection and monitoring.

• Construct Python pipelines to facilitate the collection, storage, and processing of execution logs.

• Establish and execute metrics to assess agents' performance, quality, and consistency.

• Develop automated evaluation routines (evals) for various scenarios and use cases.

• Generate analyses and reports on agent behavior, highlighting failures and potential areas for enhancement.

• Assist in the implementation of dashboards or monitoring tools.

• Document the architecture, metrics, and outcomes achieved throughout the project.

⛳️ Requirements

• Modality: TECH 4 (PhD level)

• Education: PhD

• Degree fields: Data Science, Statistics, Computer Engineering, Computer Science, or related disciplines.

🏝️ Benefits

• Comprehensive benefits package to support your health and well-being.

• Opportunities for professional development and career advancement.

• Collaborative and innovative work environment.