AI Benchmark Engineer | Native Language Specialist - Serbian - Remote

📋 Description

• Task Engineering: Evaluate coding agents.
• Asset Creation: Build native-language task environments.
• Prompting & Translation: Find failure points in your language.
• Implementation & Verification: Create robust reference solutions and verifier scripts.
• Calibration & Execution: Calibrate task difficulty across model tiers.
• Quality Assurance: 4-layer QC plus automated checks for benchmark integrity.

🎯 Requirements

• Experience: 5+ years in software engineering.
• Background: Proven track record at top tech firms or universities.
• Language: Native or near-native fluency with strong English.
• Technical Stack: Python, shell scripting, data processing.
• Workflow: Terminal/CLI workflows; familiarity with coding agents.
• Domain Expertise: Multilingual text processing; Unicode, locale, I/O, RTL as needed.

🎁 Benefits

• Flexible schedule; you control hours as contractor.
• Competitive rates; prompt payments.
• Work on impactful AI and language tech projects.
• Join a global linguistics community.
• Grow your portfolio with diverse projects.
• Meaningful, language-focused work.