Galician Language Specialist

About the role

This position channels your Galician linguistic expertise into the critical evaluation and training of large language models, where your work directly shapes how these systems handle linguistic complexity. You will design targeted test scenarios that deliberately surface model weaknesses, turning observed failures into actionable insights that improve downstream reasoning and overall performance. In this capacity, you own the systematic verification of factual accuracy and logical soundness within Galician language contexts, ensuring that error traces are captured in a reproducible manner. The role requires you to refine evaluation metrics and prompt engineering practices based on a deep analysis of model outputs, strengthening the model's ability to process diverse linguistic tasks. You will provide clear evaluation signals through documented failure modes, supporting reliable model behavior for Galician speakers across varied use cases. Your contributions will directly influence how linguistic variation and register nuances are addressed in large-scale AI systems. This position operates at the intersection of linguistic science and machine learning evaluation, requiring a high level of metacognitive communication about your work.

Key facts

What you'll do

Systematic analysis of model outputs verifies factual accuracy and logical soundness in Galician language scenarios, and captured reproducible error traces document failure modes for future reference.

Analysis of model outputs refines evaluation metrics and prompt engineering practices through systematic examination of model outputs, and adjustments to these practices strengthen how the model handles Galician language inputs and diverse linguistic tasks with precision.

Reproducible error traces guide metric refinements and prompt engineering improvements, providing clear evaluation signals that support reliable model behavior for Galician speakers in complex linguistic contexts.

You will evaluate model performance by designing test scenarios that expose weaknesses in reasoning, syntax, and regional usage within Galician language data.

Your work will involve close collaboration with engineering teams to translate linguistic findings into concrete improvements in model training and evaluation pipelines.

You will document verb conjugation patterns, noun declension errors, sentence structure anomalies, and regional dialect variations to build a comprehensive error taxonomy.

The role requires you to assess register nuances and stylistic appropriateness in model-generated Galician text across different domains and audience types.

You will contribute to the development of linguistic benchmarks that measure model robustness and adaptability to Galician-specific challenges.

Your analysis will inform the creation of targeted prompt engineering strategies that mitigate identified weaknesses and enhance model reliability.

You will maintain detailed records of experiments, including hypotheses, methodologies, and outcomes, to ensure transparency and reproducibility in linguistic evaluation.

The position involves iterative testing cycles where insights from earlier evaluations directly shape subsequent test designs and evaluation criteria.

You will communicate findings clearly to technical and non-technical stakeholders, emphasizing the business and functional impact of model behavior in Galician.

Your responsibilities include staying current with advancements in linguistic analysis techniques and AI evaluation practices relevant to low-resource language modeling.

You will support the creation of high-quality datasets that reflect the full complexity of Galician language use in real-world applications.

Requirements

The posting states a pay range of $8 to $65.

Master's or PhD study in Galician language, linguistics, or a closely related field meets the expected qualification for this role and aligns with the stated degree requirement.

Peer-reviewed publications, teaching experience, or hands-on linguistic analysis projects signal fit and demonstrate applied expertise relevant to linguistic analysis work in this specialized field.

Clear, metacognitive communication that shows your work is essential for tracing model failures and reasoning paths during evaluation, particularly when documenting verb conjugation, noun declension, sentence structure, regional dialects, and register nuances.

A secure computer and high-speed internet are contractor-supplied tools required to perform remote work in this contract role and support consistent data collection and analysis.

You must be able to work independently with minimal supervision while managing multiple analytical priorities in a contract-based environment.

Strong attention to detail is required to identify subtle linguistic errors and inconsistencies in model outputs across different Galician language tasks.

The ability to translate complex linguistic concepts into clear, structured documentation is a core requirement for success in this role.

You should be comfortable working with raw model outputs, error logs, and experimental data to derive actionable insights for system improvement.

Practical notes

Typical interview steps

Data interviews commonly include a SQL or coding exercise, a statistics question, and a case study. Candidates may be asked to design a metric, interpret an experiment, or build a small model. Some companies give a take-home analysis. Expect questions about past projects and the business impact of your work. Interviewers often evaluate how you communicate uncertainty and business impact, not only the math. Bringing a clean write-up of a past analysis to the interview is well received.

Good to know

Language training specialists design targeted prompts and analyze failure modes to evaluate model behavior in Galician language tasks. Their work shapes datasets used for large-scale AI systems and influences how models handle linguistic variation across regions and registers. Linguistic analysis in this field relies on phonology, morphology, syntax, and pragmatics to assess model outputs and surface errors systematically. General knowledge of AI evaluation metrics helps specialists communicate risk and model behavior clearly to engineering teams, supporting structured evaluation practices.

Questions to ask

Useful questions for the interview: what a typical week looks like, how work is assigned, what tools the team uses, and how feedback works. Asking how the role has changed recently and what the team wishes it had known when joining is also reasonable. Questions about the manager's priorities are especially valued.

Career growth

Data careers grow toward senior analyst, staff data scientist, or data engineering lead. Many professionals specialize in machine learning, analytics, or infrastructure. Cross-functional work with product and engineering teams becomes more important at senior levels. The field changes quickly, so continuous learning is part of the job. Professionals who can translate numbers into decisions tend to advance fastest.