Remote AI Benchmark Engineer — Native Spanish (Mexico)

Lilt; México; A distancia; MXN 344.000 - 689.000; Jornada completa

Descripción de la vacante

Lilt seeks experienced native-speaking software engineers to design, build, and validate multilingual benchmarks for evaluating large language models. This remote, freelance role focuses on high-signal tasks in your native language to test multilingual robustness without English translation crutches.

You will handle task engineering, asset creation, prompting, implementation and verification, calibration, and QA within a four-layer review workflow.

Formación

• 5+ years of industry experience in software engineering.
• Proven track record at leading technology companies or top-tier universities.
• Native or near-native fluency in the target language with high English proficiency.
• Strong Python, shell scripting, and data processing skills.
• Extensive experience with Terminal/CLI workflows and coding agents.
• Deep understanding of multilingual text processing pitfalls (Unicode, locale rules, I/O).

Responsabilidades

• Task Engineering: Evaluating Coding Agents.
• Asset Creation: Build native-language task environments with data and files in your language.
• Prompting & Translation: identify failure points in your language.
• Implementation & Verification: develop robust solutions and deterministic verifier scripts.
• Calibration & Execution: analyze logs and calibrate task difficulty across model tiers.
• Quality Assurance: participate in 4-layer quality control and automated checks.

Conocimientos

Python

Shell scripting

Data processing

Terminal/CLI workflows

Coding agents

Native language fluency

English proficiency

Educación

Graduation from top-tier engineering universities

Descripción del empleo

Lilt seeks experienced native-speaking software engineers to design, build, and validate multilingual benchmarks for evaluating large language models. This remote, freelance role focuses on high-signal tasks in your native language to test multilingual robustness without English translation crutches.

You will handle task engineering, asset creation, prompting, implementation and verification, calibration, and QA within a four-layer review workflow.