AI Benchmark Engineer | Native Language Specialist - Turkish - Remote

6 months ago

Remote, TurkeySenior

Responsibilities

Design and build high-signal Terminal-Bench tasks that evaluate coding agents in multilingual software challenges.
Create realistic datasets, files, prompts, and task environments that remain in Turkish and expose multilingual failure points.
Develop reference implementations and deterministic verifier scripts, using rubric-based judging only when necessary.
Run benchmarks against Haiku, Sonnet, and Opus model tiers, analyze execution logs, and calibrate task difficulty from Easy to Very Hard.
Participate in creation, human review, calibration review, audit, and automated LLM-based quality checks.
Ensure benchmark fairness, grammatical accuracy, reliability, and integrity.

At least 5 years of industry software engineering experience.
A proven track record at leading technology companies and/or graduation from top-tier engineering universities.
Native or near-native Turkish fluency with deep knowledge of grammar, register, and phrasing, plus high English proficiency.
Strong proficiency in Python, standard shell scripting, and data processing.
Extensive experience with Terminal/CLI-based development workflows and familiarity with coding agents.
Deep understanding of multilingual text-processing issues, including encoding and decoding, Unicode normalization, locale-dependent conventions, non-Gregorian dates, text I/O, toolchain interoperability, safe string operations, and where applicable bidirectional or RTL handling, font fallbacks, and rendering or typography.

Remote, independent-contractor work with flexible scheduling and no fixed hours or check-ins.
Competitive rates and prompt payments.
Access to diverse AI and language-technology projects and a global expert community.
Work availability fluctuates with project demand, so hours are not guaranteed and the role is not intended as a primary full-time income source.
1099 contractors do not receive health insurance, paid time off, or retirement contributions and are responsible for their own taxes.
Most accepted tasks require at least 2 hours per day or 10 hours per week.
Geographic restrictions may apply for regions subject to international embargoes or sanctions.

501-1,000 employees