Remote German AI Benchmark Engineer — Native Speaker

Lilt; Österreich; Remote; EUR 69.000 - 165.000; Teilzeit

Zusammenfassung

Lilt seeks experienced software engineers for designing and validating multilingual benchmarks. You will craft high-signal tasks and assets in your native language, focusing on robust multilingual handling and encoding.

This remote freelance role emphasizes precision, fairness, and audit-driven quality control across all stages. Responsibilities include task engineering, asset creation, prompting/translation, and implementing verification scripts, with calibration and logs review across model

Qualifikationen

• 5+ years of industry software engineering experience.
• Native or near-native fluency with high English proficiency.
• Strong understanding of multilingual text processing pitfalls and encoding issues.

Aufgaben

• Task Engineering: evaluating coding agents.
• Asset Creation: build realistic task environments using datasets/files in your native language, assets must remain in target language.
• Prompting & Translation: identify failure points in your native language.
• Implementation & Verification: write robust reference implementations and reliable verifier scripts.

Kenntnisse

Python

Shell scripting

Data processing

Terminal/CLI workflows

English proficiency

Multilingual software engineering

Ausbildung

Top-tier engineering universities

Tools

Python

Shell scripting

Jobbeschreibung

Lilt seeks experienced software engineers for designing and validating multilingual benchmarks. You will craft high-signal tasks and assets in your native language, focusing on robust multilingual handling and encoding.

This remote freelance role emphasizes precision, fairness, and audit-driven quality control across all stages. Responsibilities include task engineering, asset creation, prompting/translation, and implementing verification scripts, with calibration and logs review across model