LLM Prompt Engineer — Optimization & Validation

Remote; San Francisco (CA); Remote; USD 120,000 - 180,000; Full time

Job summary

Remote is seeking a Prompt Engineer based in the United States to own the end-to-end migration workflow for transitioning templates to LLM autoraters. You will leverage internal tools to optimize prompts and maximize model performance.

The role requires 2+ years of experience, native English, and strong data-analytics skills. You will collaborate across teams and contribute to launch readiness documentation.

Qualifications

• Native fluency in English.
• Based in United States.
• Bachelor’s, Master’s, or Doctorate degree in Computer Science, Data Science, Computational Linguistics, Human-Computer Interaction (HCI), Cognitive Science, or a related analytical field.
• At least 2 years' experience as Prompt Engineer.
• Proficient in SQL or other data analytics tools.
• Ability to quickly learn and master proprietary tools with minimal supervision.
• Excellent verbal and written communication skills.

Responsibilities

• Utilize Automatic Prompt Generation (APG) tools to create baseline prompts for complex parent-child template clusters.
• Run and supervise Automated Prompt Optimization (APO) tool, review outputs, and flag when APO reaches deadlocks or plateaus.
• Manually draft, test, and refine prompts to navigate complex template architectures and handle edge cases.
• Monitor shadowbot runs to ensure disagreements between human and LLM ratings are tracked.
• Run prompt versions against gold data to measure autorater quality against human baseline (F1, precision, recall).
• Draft technical launch readiness justifications (Launch Certification Documentation) for final.

Skills

Prompt engineering

LLM tuning

Data analysis

Communication

Education

Bachelor’s/Master’s/Doctorate in CS/DS/Computational Linguistics/HCI/Cognitive Science

Tools

SQL

Goose API

Job description

Remote is seeking a Prompt Engineer based in the United States to own the end-to-end migration workflow for transitioning templates to LLM autoraters. You will leverage internal tools to optimize prompts and maximize model performance.

The role requires 2+ years of experience, native English, and strong data-analytics skills. You will collaborate across teams and contribute to launch readiness documentation.