LLM Evaluation Scientist: Data Quality & Metrics

  • Perplexity
  • 18/05/2026
Full time Information Technology Telecommunications

Job Description

A leading tech firm in Greater London is seeking a specialist to architect automated evaluation pipelines for high-quality answers. The ideal candidate must possess a PhD or MS in a technical field and have at least 4 years of experience in data science or machine learning. You should be proficient in Python and SQL and comfortable with AWS and Databricks. This role will require you to design evaluation sets to improve overall answer quality and contribute to product changes based on evaluation metrics.