AI Benchmark Engineer | Native Language Specialist - Dutch

What You'll Deliver:

• Evaluating coding agents with high-signal, multilingual Terminal-Bench tasks.
• Building realistic task environments using native-language datasets and files.
• Writing reliable verifier scripts and calibrating difficulty across model tiers.

Qualifications:

• 1+ years of software engineering experience with a proven track record at top companies or universities.
• Native Dutch fluency with high English proficiency and strong Python/shell skills.
• Deep understanding of multilingual text processing, encoding, Unicode, and locale conventions.

Why Collaborate with Lilt:

• Flexible freelance schedule with no fixed hours or micromanaging.
• Competitive rates and prompt payments for high-quality work.
• Contribute to cutting-edge AI and language technology with a global community.

What to Consider:

• This is a supplemental income opportunity, not a full-time primary source.
• Work availability fluctuates with project demand, requiring reliable commitment.
• As a 1099 contractor, you are responsible for taxes and receive no employee benefits.