🛠 Tech Stack

💼 About This Role

You'll build multilingual evaluation tasks for large language models, focusing on terminal-based software challenges. Your work will measure multilingual robustness across encoding and locale edge cases. This is a remote freelance role with flexible hours.

🎯 What You'll Do

• Design and build benchmark tasks for coding agents
• Create realistic task environments using native language data
• Develop robust reference implementations and verifier scripts
• Calibrate task difficulty across multiple model tiers

📋 Requirements

• 5+ years of software engineering experience
• Native Turkish fluency with deep grammar knowledge
• Strong proficiency in Python, shell scripting, and data processing
• Experience with terminal/CLI development workflows

✨ Nice to Have

• Background at leading tech companies or top-tier universities
• Knowledge of Unicode normalization and locale-dependent conventions
• Familiarity with coding agents

🎁 Benefits & Perks

• 🗓️ Flexible schedule as an independent contractor
• 💰 Competitive rates with prompt payments
• 🌍 Work on cutting-edge AI and language technology
• 🤝 Join a global community of language professionals
• 📚 Access to diverse, innovative projects

📨 Hiring Process

Submit application with CV, complete GenAI assessment, finalize onboarding.

[email protected]