Post a Job
All remote jobs
Welo Global

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

AI Summary
Welo Global is seeking a senior Italian-speaking Prompt Engineer to migrate and optimize template workflows for LLM autoraters. The contractor will use automated prompt-generation and optimization tools, manually improve prompts for difficult edge cases, and monitor model-versus-human evaluation results. Core work includes measuring quality with F1, precision, and recall, identifying performance issues, and preparing launch-readiness documentation. The role requires at least four years of prompt-engineering experience, strong LLM evaluation knowledge, analytical capability, and native Italian with fluent English. It is a remote freelance opportunity restricted to candidates based in Italy.
Apply for this job View company
Remote from
Italy
Salary
Undisclosed
Department
Data Science & Analytics
Employment
Contract
Experience
Senior
Published
Apply before
8 Dec 2026
Listing views
24
Application actions
2
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 Italian and fluent in English.

  • Location: Must be based in Italy.

  • 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 deep prompt-engineering expertise, rigorous LLM evaluation, and the ability to resolve tooling failures and complex edge cases independently. The candidate must combine linguistic reasoning, data analysis, and production-quality documentation.

Salary analysis

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

Estimated job median (per hour)Highly competitive
$72.50
US market range (per hour)$55–$90
AI insightThe hourly pay period is inferred from the job context; it was not explicitly stated by the employer. No employer pay was disclosed. Hourly compensation is inferred from the remote, part-time freelance structure; the displayed USD range is an AI estimate for a senior prompt-engineering contractor and is not verified employer compensation.

Core skills

Skills and capabilities most closely associated with this opportunity.

Prompt engineeringLarge language modelsAutomated prompt optimizationAutomatic prompt generationLLM evaluationPrompt testingStructured output designClassification modelingF1 score analysisPrecision and recallSQLError analysisComputational linguisticsItalian language fluencyTechnical documentation
Sample interview questions
How would you improve a prompt that performs well on common cases but fails on a small set of complex edge cases?

I would first segment the failures by pattern and compare model outputs with the gold data and human ratings. I would test targeted prompt changes, such as clearer decision rules, counterexamples, output constraints, and few-shot examples, then validate each version against both the edge-case set and the broader regression suite.

How do you use precision, recall, and F1 score when evaluating an LLM autorater?

I use precision to assess how often positive predictions are correct, recall to assess how many true positives are captured, and F1 to balance the two. I also inspect class-level metrics and confusion patterns because an aggregate F1 score can obscure critical failure modes in specific categories.

Describe how you would respond when an automated prompt-optimization workflow reaches a plateau.

I would review the optimization history, inspect the evaluated examples, and determine whether the issue is prompt ambiguity, insufficient examples, data-quality problems, or a model limitation. I would then introduce manually designed prompt variants, revise the evaluation set if justified, and document the hypothesis and results before resuming automated optimization.

What makes a prompt reliable for strict structured outputs?

A reliable prompt defines the expected schema unambiguously, provides explicit field-level rules, constrains allowed values, and includes examples for difficult cases. I would also validate outputs programmatically, test adversarial and boundary inputs, and use retries or repair logic only where the product workflow permits it.

How would you communicate launch readiness for an LLM autorater to stakeholders?

I would prepare concise documentation covering the intended use case, prompt version, evaluation methodology, benchmark results, known limitations, edge-case behavior, and monitoring plan. I would clearly distinguish validated performance from open risks and state the criteria used to recommend launch.

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