Post a Job
All remote jobs
Welo Global

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

AI Summary
Welo Global is seeking a senior French-speaking Prompt Engineer to migrate and optimize template workflows for LLM-based autoraters. The role combines automated prompt generation and optimization with hands-on prompt design for complex edge cases and structured classification tasks. The engineer will evaluate quality against gold data and human baselines using metrics including F1, precision, and recall, while documenting launch readiness. Candidates need at least four years of prompt-engineering experience, strong LLM evaluation skills, SQL or analytics capability, and native French with fluent English. This is a remote freelance engagement restricted to professionals based in France.
Apply for this job View company
Remote from
France
Salary
Undisclosed
Department
Data Science & Analytics
Employment
Contract
Experience
Senior
Published
Apply before
8 Dec 2026
Listing views
12
Application actions
0
Application toolkit

Make your next move.

Prepare your resume, explore your fit, and draft a cover letter for this opportunity.

Opportunity details

About this role.

 We are seeking a Prompt Engineer to be responsible for the end-to-end technical migration workflow for transitioning templates to LLM autoraters. 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.  

  • Manually draft, 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.

  • Monitor shadowbot runs to ensure sufficient disagreements (between human and LLM ratings) are registered, generated, and tracked.  

  • Run prompt versions against established gold data to continuously measure autorater quality 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, or a related analytical 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: Strong proficiency in identifying error 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. 

Compensation

Additional Information

Apply now >

This job listing has been manually reviewed by the Jobicy Trust & Safety Team for compliance with our posting guidelines, including verification of the company's legitimacy, accuracy of job details, clarity of remote work policy, and absence of misleading or fraudulent content.

Role DNA

A quick view of the complexity, pace, ownership and collaboration implied by the job description.

Job Complexity

5/5
EasyHard

Pace & Pressure

4/5
RelaxedFast-paced

Autonomy Level

5/5
GuidedFull ownership

Communication Load

4/5
IndependentCollaborative
AI insightThis is a senior technical role requiring independent optimization of LLM prompts, diagnosis of tool failures, and quantitative model-quality evaluation. Success depends on combining linguistic judgment, experimentation, analytics, and clear technical documentation.

Salary analysis

Estimated compensation compared with the broader US market for similar roles.

Estimated job median (per hour)Market rate
$60
US market range (per hour)$45–$80
AI insightThe hourly pay period is inferred from the job context; it was not explicitly stated by the employer. No employer compensation was disclosed. The hourly cadence is inferred from the remote, part-time freelance engagement; estimated USD hourly market range is an AI estimate, not verified salary research.

Core skills

Skills and capabilities most closely associated with this opportunity.

Prompt engineeringLarge language modelsAutomated prompt optimizationPrompt testingLLM evaluationClassification modelingError analysisF1 score analysisPrecision and recallSQLData analyticsFrench language fluencyTechnical documentationComputational linguistics
Sample interview questions
How would you approach optimizing a prompt for a strict multi-class classification task?

I would first define the output schema and evaluation criteria, establish a baseline prompt, and test it against representative gold data. I would analyze failure patterns by class and error type, then iteratively apply clear instructions, few-shot examples, constraints, and targeted edge-case guidance while measuring precision, recall, and F1 after each change.

What would you do if an Automated Prompt Optimization workflow reached a plateau?

I would validate that the evaluation set is representative and inspect the optimizer outputs for repeated failure modes or conflicting instructions. I would then manually formulate hypotheses, simplify or restructure the prompt, add targeted examples for difficult cases, and retest changes against both gold data and broader validation samples.

How do you ensure that improvements to an LLM prompt generalize beyond a gold dataset?

I separate development, validation, and holdout examples, including adversarial and edge-case samples where possible. I track metrics by segment rather than relying only on an aggregate score, review qualitative errors, and use shadow runs against human ratings to detect regressions or overfitting.

Describe how you would investigate disagreement between human raters and an LLM autorater.

I would first verify annotation guidelines and the consistency of the human labels, then categorize disagreements by ambiguity, missing context, label-boundary issues, and model reasoning failures. Based on the analysis, I would improve the prompt, examples, or decision criteria and document any cases requiring a policy clarification rather than a prompt-only solution.

How would you document launch readiness for a new autorater prompt version?

I would summarize the prompt version, target task, data coverage, evaluation methodology, quantitative results, known limitations, and comparison with the human baseline. The documentation would include unresolved risks, rollback criteria, monitoring requirements, and evidence that key edge cases and output-format requirements were validated.

This analysis is generated from the job description. Salary estimates, role characteristics and sample answers are guidance, not employer-provided facts.
Next step

Apply now.

Follow the employer’s application method and review Jobicy’s safety guidance before sharing personal information.

Did you apply?Let us know, and we’ll help you track your application.

Continue on the employer website

Protect your personal information and never pay to secure an interview or job offer. .

Log in to save
One quick step before you apply

Sign in to continue.

Sign in or create a free account to continue to the employer's application.
Add alert
Job Search Safety Tips
Here are some tips to help you search and apply for jobs safely:
Watch out for suspicious jobs Don't apply for jobs that offer high pay for little work or offer to hire you without an interview. Read more ›
Check the employer's profile Make sure you're applying for a trustworthy job by visiting the employer's profile and learning more about them. Read more ›
Protect your information Don't share personal details like your bank account or government-issued ID on suspicious websites or messengers. Read more ›
Report jobs that feel unsafe If you see a job that seems misleading, inappropriate or discriminatory, report it for going against our policies and we'll review it.
Share this job
Jobs Talent AI Tools Salaries
Menu