Senior Prompt Engineer — LLM Tuning & Automation (Spain)

Remote; San Francisco (CA); Remote; USD 100,000 - 145,000; Full time

Job summary

Remote is seeking a Prompt Engineer based in Spain to manage end-to-end migration workflows for templates to LLM autoraters. You will leverage APG and APO tools to optimize prompts, review outputs, and handle edge cases where tooling is lacking or broken.

You will monitor shadowbot runs, compare results against gold data, and report accuracy metrics (F1, precision, recall). Strong SQL/data analytics skills and excellent communication are required.

Qualifications

• Native fluency in Spanish and fluent in English.
• Bachelor’s, Master’s, or Doctorate in Computer Science, Data Science, Computational Linguistics, HCI or related field.

Responsibilities

• Oversee end-to-end migration workflow for templates to LLM autoraters.
• Utilize APG to create baseline prompts for template clusters.
• Supervise APO tool and flag deadlocks or plateaus.
• Draft and test prompts for complex template architectures and edge cases.
• Monitor shadowbot runs and ensure disagreements between human and LLM ratings are tracked.
• Evaluate prompts against gold data, compute F1, precision, recall.

Skills

Spanish native

English fluent

Education

BS/MS/PhD CS/DS/Computational Linguistics

Tools

SQL

Goose API

Job description

Remote is seeking a Prompt Engineer based in Spain to manage end-to-end migration workflows for templates to LLM autoraters. You will leverage APG and APO tools to optimize prompts, review outputs, and handle edge cases where tooling is lacking or broken.

You will monitor shadowbot runs, compare results against gold data, and report accuracy metrics (F1, precision, recall). Strong SQL/data analytics skills and excellent communication are required.