AI Benchmark Engineer | Native Language Specialist - Japanese - Remote
Core
Design, build, and validate rigorous evaluation benchmarks (Terminal-Bench) to test large language models on multilingual software challenges, specifically focusing on non-English data processing and locale/encoding edge cases.
Role type
Native language specialist / AI benchmark engineer (freelance)
Builds
High-signal multilingual benchmark tasks and deterministic verifier scripts for coding agents
Domain
AI evaluation / Multilingual software engineering / Terminal workflows
Deliverable
production ML models
Required skills
Python, shell scripting, data processing, terminal/CLI development, coding agents, multilingual text processing (encoding/decoding, Unicode, locale conventions)
Preferred skills
Native or near-native fluency in Japanese, deep understanding of grammar/register/phrasing, high English proficiency, background at leading tech companies or top-tier engineering universities
Technologies
Python, Shell, CLI, Terminal-Bench, LLMs (Haiku, Sonnet, Opus)
Responsibilities
Create realistic task environments using native language assets, find failure points in AI models within native language contexts, write reliable verifier scripts, analyze execution logs to calibrate task difficulty, participate in 4-layer human quality control process
Seniority
Mid-level, hands-on IC