About the role
Remote part-time freelance role for a senior prompt engineer based in Italy: migrate rating templates to LLM autoraters using automatic prompt generation and optimization tools, write and refine prompts by hand for edge cases, and measure autorater quality against human ratings (F1, precision, recall).
Experience
Native Italian and fluent English; at least 4 years as a prompt engineer, with experience tuning LLMs for structured outputs and classification; degree in computer science, data science, computational linguistics, HCI, cognitive science or a related field; SQL or other data analysis tools.
Education
Bachelor's, Master's or Doctorate in Computer Science, Data Science, Computational Linguistics, HCI, Cognitive Science or a related analytical field.
Selection process
Apply through the official Lever form.
Eligibility
Must be based in Italy (as stated on the listing)