Summary

Member of technical staff in data analysis and evaluation, focused on ensuring the quality, reliability, and performance of large language models. You will design and oversee data collection with human annotators, apply statistical methods to evaluate datasets, and assess robustness and generalisability across use cases. The role is remote-friendly and involves collaborating with researchers, engineers, and data annotators.

Responsibilities

• Design and oversee data collection tasks
• Support and coordinate human annotators
• Develop statistical methods for dataset evaluation
• Assess dataset quality, reliability, and biases
• Analyze model robustness and generalisability
• Train and fine-tune llms on distributed infrastructure
• Conduct experiments to evaluate model performance