An organization is building a rigorous, verifiable evaluation suite of Terminal-Bench tasks designed to test the limits of large language models on multilingual software challenges. The goal is to measure multilingual robustness across prompt language effects, non-English data processing, and complex locale/encoding edge cases in terminal workflows. They are seeking experienced native-speaking software engineers to design, build, and validate these benchmarks.
You will create high-signal, high-quality tasks that genuinely test a model's ability to handle multilingual environments without relying on English translation crutches.
What you will do.
- Task Engineering: Evaluating Coding Agents.
- Asset Creation: Build realistic task environments using datasets and files in your native language. Crucially, these assets must remain in the target language to genuinely measure multilingual handling.
- Prompting & Translation: Finding failure points where AI does not work, in your native language.
- Implementation & Verification: Support the development of robust solutions (reference implementations) and write highly reliable, deterministic verifier scripts.
- Calibration & Execution: Analyze execution logs and calibrate task difficulty (Easy to Very Hard) using standard Terminal-Bench run configurations against various model tiers.
- Quality Assurance: Participate in a rigorous, 4-layer human quality control process (creation, human review, calibration review, and audit) alongside automated LLM-based checks to ensure fairness, grammatical accuracy, and benchmark integrity.
What they ask
- Experience: 1+ years of industry experience in software engineering.
- Background: Proven track record at leading technology companies and/or graduation from top-tier engineering universities.
- Language: Native or near-native fluency in Dutch, with a deep understanding of its grammar, register, and phrasing rules. High English proficiency.
- Technical Stack: Strong proficiency in Python, standard shell scripting, and data processing.
- Workflow: Extensive experience with Terminal/CLI-based development workflows and a working familiarity with coding agents.
- Domain Expertise: Deep technical understanding of multilingual text processing pitfalls, including:
- Encoding/decoding robustness and Unicode normalization.
- Locale-dependent conventions (collation, casing, non-Gregorian dates).
- Text I/O, toolchain interoperability, and safe string operations.
- (For specific languages) Bidirectional/RTL handling, font fallbacks, and rendering/typography in UI or artifacts.
Practical
- Not ideal as a full-time job or primary income source. Work availability fluctuates with project demand, making this better suited as a supplemental income stream.
- Requires reliable availability and commitment. Once you accept a task, quality work and on-time delivery are expected.
- Geographic restrictions may apply. Contractors cannot be engaged in regions subject to international embargo or sanctions.
- As an independent contractor, you are solely responsible for your own tax obligations.
How to apply
View the full assignment text and application details once your tailored application is ready.
Order a tailored application to view the full assignment and application details.
More context, less searching.
You get enough context to judge whether this job is relevant. The full brief, client details and next steps stay available inside the app.