[All remote jobs](https://jobicy.com/jobs.md)[![Welo Global logo](https://jobicy.com/data/server-nyc0409/galaxy/mercury/2026/06/83c40f94-221.webp)](https://jobicy.com/company/welo-global.md)[Welo Global](https://jobicy.com/company/welo-global.md) # Project Lion – Senior Prompt Engineer – Spain (Remote, Part-Time) AI Summary Senior Prompt Engineer will lead the technical migration of template workflows to LLM-based autoraters. The role combines automated prompt generation and optimization with hands-on prompt design for difficult template structures and edge cases. It requires evaluating model quality against human baselines using metrics such as F1, precision, and recall, as well as preparing launch-certification documentation. Candidates need native Spanish, fluent English, substantial LLM prompt-engineering experience, and strong analytical capability with SQL or comparable tools. This is a remote freelance engagement restricted to candidates based in Spain.[Apply for this job](#job-application)[View company](https://jobicy.com/company/welo-global.md)ShareRemote from[Spain](https://jobicy.com/job-region/spain.md)SalaryUndisclosedDepartment[Software Engineering](https://jobicy.com/categories/engineering.md)EmploymentContractExperienceSeniorPublished8 Nov 2026Apply before8 Dec 2026Listing views32Application actions3Application 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 Spanish and fluent in English. * Location: Must be based in Spain. * 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 Show more [Apply now >](https://jobicy.com/jobs/159780-project-lion-senior-prompt-engineer-spain-remote-part-time.md) > Annual salary information is not provided for this position. Explore salary ranges for similar roles in our [Salary Directory ›](https://jobicy.com/salaries.md) * ![Upload CV](data:image/svg+xml;base64,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) ### Upload your resume now To unlock remote work opportunities and be discovered by global employers. 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 5/5EasyHard ### Pace & Pressure 4/5RelaxedFast-paced ### Autonomy Level 5/5GuidedFull ownership ### Communication Load 4/5IndependentCollaborative AI insightThe position requires at least four years of specialized prompt-engineering experience and ownership of complex LLM evaluation and optimization workflows. Success depends on independently resolving tooling failures, diagnosing model-quality issues, and producing technically defensible launch documentation. ## Salary analysis Estimated compensation compared with the broader US market for similar roles. Estimated job median (per hour)Market rate$55US market range (per hour)$40–$750$82.50 AI insightThe hourly pay period is inferred from the job context; it was not explicitly stated by the employer. No employer salary was disclosed. The hourly cadence is inferred from the remote freelance, part-time nature of the role. Estimated market compensation is USD 40–75 per hour, with an estimated midpoint of USD 55 per hour; this is an AI estimate rather than verified salary research. ## Core skills Skills and capabilities most closely associated with this opportunity. [Prompt engineering](https://jobicy.com/jobs?search_keywords=Prompt%20engineering.md)[Large language models](https://jobicy.com/jobs?search_keywords=Large%20language%20models.md)[Prompt optimization](https://jobicy.com/jobs?search_keywords=Prompt%20optimization.md)[Automated prompt generation](https://jobicy.com/jobs?search_keywords=Automated%20prompt%20generation.md)[LLM evaluation](https://jobicy.com/jobs?search_keywords=LLM%20evaluation.md)[Model performance analysis](https://jobicy.com/jobs?search_keywords=Model%20performance%20analysis.md)[F1 score analysis](https://jobicy.com/jobs?search_keywords=F1%20score%20analysis.md)[Precision and recall](https://jobicy.com/jobs?search_keywords=Precision%20and%20recall.md)[SQL](https://jobicy.com/jobs?search_keywords=SQL.md)[Data analysis](https://jobicy.com/jobs?search_keywords=Data%20analysis.md)[Few-shot learning](https://jobicy.com/jobs?search_keywords=Few-shot%20learning.md)[Chain-of-thought prompting](https://jobicy.com/jobs?search_keywords=Chain-of-thought%20prompting.md)[Technical documentation](https://jobicy.com/jobs?search_keywords=Technical%20documentation.md)[Spanish language fluency](https://jobicy.com/jobs?search_keywords=Spanish%20language%20fluency.md)[English communication](https://jobicy.com/jobs?search_keywords=English%20communication.md) Sample interview questionsHow would you approach improving an LLM prompt that performs poorly on a complex classification template?I would first segment failures by template type, label, and error pattern, then compare outputs with gold data and human ratings. I would test targeted changes to instructions, output schemas, examples, and edge-case handling, measuring each version with precision, recall, and F1 before promoting it. What do you do when an automated prompt-optimization workflow reaches a plateau? I validate that the evaluation set is representative and inspect whether the optimizer is overfitting to a narrow set of examples. I then introduce controlled manual hypotheses, revise the prompt structure or examples, and document the experiments so the next iteration is measurable and reproducible. How would you monitor disagreement between human evaluators and an LLM autorater? I would track disagreement rates by task, category, prompt version, and confidence level. I would prioritize recurring or high-impact disagreement clusters for qualitative review, determine whether the issue is ambiguous labeling or model behavior, and use the findings to refine the prompt or evaluation data. How do you ensure a prompt produces strict, structured output? I define an explicit schema, specify allowed values and formatting rules, provide representative few-shot examples, and state how to handle missing or ambiguous inputs. I also test adversarial and malformed cases and add automated validation to detect schema violations before scoring downstream results. How would you explain launch readiness for an LLM autorater to non-technical stakeholders? I would summarize the task scope, evaluation data, key quality metrics, known limitations, and safeguards in concise language. I would clearly state whether acceptance thresholds were met, identify residual risks, and provide a monitoring and rollback plan for the launch period. Next step ## Apply now. Follow the employer’s application method and review Jobicy’s safety guidance before sharing personal information. Keep exploring ## Related remote jobs. * ![Welo Global logo](https://jobicy.com/data/server-nyc0409/galaxy/mercury/2026/06/83c40f94-221.webp) Welo Global Nov 8 New ### [MSR Project – Japanese Culture Expert](https://jobicy.com/jobs/159811-msr-project-japanese-culture-expert.md) Overview Are you passionate about languages, writing, and quality evaluation? We are launching an exciting language evaluation project and are looking for Japanese-speaking experts to join our team. What you… * ![Welo Global logo](https://jobicy.com/data/server-nyc0409/galaxy/mercury/2026/06/83c40f94-221.webp) Welo Global Nov 8 New ### [Maps Personalization Relevance Rater – Japanese (Japan)](https://jobicy.com/jobs/159810-maps-personalization-relevance-rater-japanese-japan.md) Contract type: Freelance Language: Japanese (Japan) Estimated volume: 8 – 10 hours Start date: The project runs on a weekly basis. We are looking for qualified raters to support a… * ![Binance logo](https://jobicy.com/data/server-nyc0409/galaxy/mercury/2025/06/bc822f38-221.jpg) Binance Nov 8 New ### [Cloud AI Engineer (Legal & Compliance)](https://jobicy.com/jobs/159740-cloud-ai-engineer-legal-compliance.md) Binance is a leading global blockchain ecosystem behind the world’s largest cryptocurrency exchange by trading volume and registered users. We are trusted by 300+ million people in 100+ countries for… * ![SeatGeek logo](https://jobicy.com/data/server-nyc0409/galaxy/mercury/2025/06/72d8f3a6-221.jpeg) SeatGeek Nov 8 New ### [Senior Fullstack Engineer, FanX AI](https://jobicy.com/jobs/159745-senior-fullstack-engineer-fanx-ai.md) SeatGeek believes live events are powerful experiences that unite humans. With our technological savvy and fan-first attitude we’re simplifying and modernizing the ticketing industry. By catering to both consumers and… * ![Truelogic logo](https://jobicy.com/data/server-nyc0409/galaxy/mercury/2025/06/e7ae6cb6-221-1.png) Truelogic Nov 8 New ### [Senior Full-Stack Growth Engineer – Marketing & Analytics](https://jobicy.com/jobs/159736-senior-full-stack-growth-engineer-marketing-analytics.md) About Truelogic At Truelogic we are a leading provider of nearshore staff augmentation services headquartered in New York. For over two decades, we’ve been delivering top-tier technology solutions to companies… * ![Caylent logo](https://jobicy.com/data/server-nyc0409/galaxy/mercury/2025/06/9ed8d81b-221.jpg) Caylent Nov 8 New ### [Forward Deployed Engineer](https://jobicy.com/jobs/159734-forward-deployed-engineer-9.md) Caylent is an AI-first cloud services company that helps organizations turn ambitious ideas into meaningful business impact. As an AWS Premier Tier Services Partner and a charter member of Anthropic’s… * ![TRM Labs logo](https://jobicy.com/data/server-nyc0409/galaxy/mercury/2025/06/34aa038c-221.png) TRM Labs Nov 8 New ### [Senior AI Engineer (AI Automation)](https://jobicy.com/jobs/159726-senior-ai-engineer-ai-automation.md) Build a Safer World. TRM Labs provides AI-powered intelligence solutions that help public and private sector agencies investigate and disrupt crime. TRM’s platforms enable investigators to trace illicit activity, build… * ![Truelogic logo](https://jobicy.com/data/server-nyc0409/galaxy/mercury/2025/06/e7ae6cb6-221-1.png) Truelogic Nov 8 New ### [Implementation Engineer – Technology Industry](https://jobicy.com/jobs/159722-implementation-engineer-technology-industry.md) About Truelogic At Truelogic we are a leading provider of nearshore staff augmentation services headquartered in New York. For over two decades, we’ve been delivering top-tier technology solutions to companies… * ![Juniper Square logo](https://jobicy.com/data/server-nyc0409/galaxy/mercury/2022/01/90c359a8bed816e81ea39fa33a8314f3.png) Juniper Square Nov 8 New ### [Director, Engineering (Platform)](https://jobicy.com/jobs/159720-director-engineering-platform-2.md) About Juniper Square Private markets are one of the largest, most complex, and most underserved corners of global finance. Our mission at Juniper Square is to unlock their full potential…. * ![Oowlish Technology logo](https://jobicy.com/data/server-nyc0409/galaxy/mercury/2025/06/c279fe91-221.jpg) Oowlish Technology Nov 8 New ### [Senior Android Engineer (Kotlin & AWS)](https://jobicy.com/jobs/159719-senior-android-engineer-kotlin-aws-2.md) Join Our Team Oowlish, one of Latin America’s rapidly expanding software development companies, is seeking experienced technology professionals to enhance our diverse and vibrant team. As a valued member of… [Browse all jobs](https://jobicy.com/jobs.md)