🛠 Tech Stack

💼 About This Role

You'll design and validate multilingual benchmark tasks for large language models, focusing on terminal-based workflows and non-English data processing. Your work will ensure rigorous evaluation of AI multilingual robustness.

🎯 What You'll Do

• Design and build realistic multilingual task environments
• Write deterministic verifier scripts for benchmark tasks
• Analyze execution logs to calibrate task difficulty
• Participate in multi-layer quality assurance process

📋 Requirements

• 5+ years of industry software engineering experience
• Native fluency in Chinese Mandarin
• Strong proficiency in Python and shell scripting
• Deep understanding of multilingual text processing

✨ Nice to Have

• Experience with coding agents or LLM evaluation
• Proven track record at leading tech companies
• Familiarity with Unicode normalization and locale conventions

🎁 Benefits & Perks

• 🗓️ Flexible schedule as an independent contractor
• 💰 Competitive rates with prompt payments
• 🌍 Work on cutting-edge AI projects
• 🤝 Global community of language professionals

📨 Hiring Process

Estimated timeline: 1-2 weeks

1. 1Submit application with CV· 30 min
2. 2Complete GenAI assessment· 1 hour
3. 3Finalize onboarding and profile set-up· 1 hour

[email protected]