Project Lion – Senior Prompt Engineer – France (Remote, Part-Time)

Welo Global; United States; Remoto; USD 100.000 - 145.000; Tempo integral

Resumo da vaga

Jobicy is seeking a Prompt Engineer based in France to manage end-to-end migration workflows for templates to LLM autoraters. You will use internal tools to leverage prompt engineering techniques to maximize model performance.

The role requires native French, fluent English, and a strong background in data analysis, prompts tuning, and complex template navigation. Collaborative launch readiness documentation is also part of the job.

Qualificações

• Bachelor’s, Master’s or Doctorate in CS/Data Science/Computational Linguistics or related analytical field.
• 4+ years’ experience as Prompt Engineer with LLM tuning experience.
• Proficiency in identifying error patterns and analyzing model performance.

Responsabilidades

• Utilize APG tools to create baseline prompts for complex template clusters.
• Run and supervise APO tool outputs, flag deadlocks or plateaus.
• Manually draft and refine prompts for complex architectures and edge cases.
• Monitor shadowbot runs for disagreements between human and LLM ratings.
• Evaluate prompt versions against gold data and measure accuracy metrics.
• Draft Launch Certification Documentation for technical readiness.

Conhecimentos

Prompt engineering

LLM tuning

Data analysis

Communication

French language

English fluency

Formação

Bachelor’s degree in Computer Science or related field

Master’s degree in related field

Doctorate in related analytical field

Ferramentas

SQL

APG tools

Goose API

Descrição da vaga

We are seeking a Prompt Engineer to be responsible for the end-to-end technical migration workflow for transitioning templates to LLMautoraters. The role is required to use client’s internal tools to leverage prompt engineering techniques to maximize model performance.

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 the outputs, and flag when the APO reaches deadlocks or plateaus.
• Manuallydraft, test, and refine prompts to navigate complex template architectures, overcome anti-patterns, and handle edge cases where tooling is lacking or broken. Solve edge-case scenarios by designing and refining manual prompts.
• Monitorshadowbotruns to ensure sufficient disagreements (between human and LLM ratings) are registered, generated, and tracked.
• Run prompt versions against established gold data to continuously measureautoraterquality against the human crowd baseline, calculating accuracy metrics such as F1 scores, precision, and recall.
• Draft technical launch readiness justifications (Launch Certification Documentation) for final.

Requirement:

• Language Skills: Native fluency in French and fluent in English.
• Location: Must be based in France.
• Education: Bachelor’s, Master’s, or Doctorate degree in Computer Science, Data Science, Computational Linguistics, Human-Computer Interaction (HCI), Cognitive Science, ora relatedanalytical field.
• Prompt Engineering & AI Expertise: At least 4 years’ experience as Prompt Engineer. Proven experience tuning Large Language Models (LLMs)for strict, structured outputs, complex classification tasks, and familiarity with chain-of-thought and few-shot learning.
• Data Analysis: Strongproficiencyinidentifyingerror patterns, analyzing model performance, and using SQL or other data analytics tools.
• Technical Agility: Ability to quickly learn and master proprietary tools with minimal supervision.
• Communication: Excellent verbal and written communication skills.

Optional / Preferred Skills:

• Familiarity with enterprise-grade LLM interfaces like the Goose API.
• Experience in AI model evaluation, data science, computational linguistics, or software engineering.
• Hands‑on experience with Automated Prompt Optimization (APO) systems or tuning workflows.
• Linguistic expertise, including an understanding of semantics and logic.