We are building a rigorous, verifiable evaluation suite of Terminal-Bench tasks designed to test the limits of large language models on multilingual software challenges. Our goal is to measure multilingual robustness across prompt language effects, non-English data processing, and complex locale/encoding edge cases…
We are building a rigorous, verifiable evaluation suite of Terminal-Bench tasks designed to test the limits of large language models on multilingual software challenges. Our goal is to measure multilingual robustness across prompt language effects, non-English data processing, and complex locale/encoding edge cases…
We are building a rigorous, verifiable evaluation suite of Terminal-Bench tasks designed to test the limits of large language models on multilingual software challenges. Our goal is to measure multilingual robustness across prompt language effects, non-English data processing, and complex locale/encoding edge cases…
We are building a rigorous, verifiable evaluation suite of Terminal-Bench tasks designed to test the limits of large language models on multilingual software challenges. Our goal is to measure multilingual robustness across prompt language effects, non-English data processing, and complex locale/encoding edge cases…
We are building a rigorous, verifiable evaluation suite of Terminal-Bench tasks designed to test the limits of large language models on multilingual software challenges. Our goal is to measure multilingual robustness across prompt language effects, non-English data processing, and complex locale/encoding edge cases…
We are building a rigorous, verifiable evaluation suite of Terminal-Bench tasks designed to test the limits of large language models on multilingual software challenges. Our goal is to measure multilingual robustness across prompt language effects, non-English data processing, and complex locale/encoding edge cases…
Are you a Dutch, German or French-speaking professional who instinctively spots gaps in language reasoning and understands the complex realities of language use? Do you have 8 to 20 hours per week available alongside your main job or consulting projects? Join us in shaping how AI understands and applies linguistic…
Welo Data, part of Welocalize, is a global AI data company with 500,000+ contributors delivering high-quality, ethical data to train the world’s most advanced AI systems. We’re building smarter, more human AI with a diverse community in 100+ countries.
Remote part-time freelance role for a senior prompt engineer based in Italy: migrate rating templates to LLM autoraters using automatic prompt generation and optimization tools, write and refine prompts by hand for edge cases, and measure autorater quality against human ratings (F1, precision, recall).
Talent network for Italian speakers run by Welo Data: join the contributor database for flexible remote projects in annotation, evaluation of search results, ads or chatbot responses, and prompt creation. This is not an active job opening; Welo Data contacts you when a project matches, with scope, timeline and pay.