Remote, flexible hourly contract for senior software engineers working on agentic AI: design and refine workflows where AI plans, writes, tests and iterates on code, evaluate AI-generated code for correctness, efficiency and security, create real-world coding challenges and benchmarks, identify failure modes of autonomous agents and improve evaluation rubrics and test harnesses. Task-based, asynchronous work on your own schedule.
Remote hourly contract for senior software engineers: design coding benchmarks and data pipelines used to evaluate frontier AI models, analyse AI-generated code for correctness and quality, build realistic evaluation scenarios and give detailed technical feedback. The listing states a 3-month initial contract with possible extension; full-time availability is preferred.
Remote contract work for application security specialists: build small test applications and deterministic test cases used to evaluate how AI tools and scanners assess application security, write answer keys and documentation, and review peers’ contributions. The project focuses on security risks specific to applications that use large language models.
Remote contract work for applied scientists and data scientists: run statistical analyses, build and validate machine learning models, evaluate AI model answers on statistics, machine learning and experimentation problems, and write expert-level prompts, datasets and reference solutions. No prior AI-training experience is required.
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 in terminal workflows. We 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. Note this is a remote, freelance opportunity
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 in terminal workflows. We 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. Note this is a remote, freelance opportunity
We’re looking for coding specialists who live and breathe algorithms, data structures, software architecture, frontend and backend development, cloud infrastructure, and systems programming—and who can do so fluently in Arabic. You’ll challenge advanced language models on topics like asynchronous programming, RESTful API integration, memory management, object-oriented design, secure coding practices, and debugging distributed systems—documenting every failure mode so we can harden model reasoning. On a typical day, you will converse with the model on software engineering tasks and technical scenarios in Arabic, verify logical accuracy and coding fluency, assess naturalness and correctness of
We’re looking for coding specialists who live and breathe algorithms, data structures, software architecture, frontend and backend development, cloud infrastructure, and systems programming—and who can do so fluently in Spanish (Spain). You’ll challenge advanced language models on topics like asynchronous programming, RESTful API integration, memory management, object-oriented design, secure coding practices, and debugging distributed systems—documenting every failure mode so we can harden model reasoning. On a typical day, you will converse with the model on software engineering tasks and technical scenarios in Spanish (Spain), verify logical accuracy and coding fluency, assess naturalness
We’re looking for coding specialists who live and breathe algorithms, data structures, software architecture, frontend and backend development, cloud infrastructure, and systems programming—and who can do so fluently in Dutch. You’ll challenge advanced language models on topics like asynchronous programming, RESTful API integration, memory management, object-oriented design, secure coding practices, and debugging distributed systems—documenting every failure mode so we can harden model reasoning. On a typical day, you will converse with the model on software engineering tasks and technical scenarios in Dutch, verify logical accuracy and coding fluency, assess naturalness and correctness of D
We’re looking for coding specialists who live and breathe algorithms, data structures, software architecture, frontend and backend development, cloud infrastructure, and systems programming—and who can do so fluently in Chinese. You’ll challenge advanced language models on topics like asynchronous programming, RESTful API integration, memory management, object-oriented design, secure coding practices, and debugging distributed systems—documenting every failure mode so we can harden model reasoning. On a typical day, you will converse with the model on software engineering tasks and technical scenarios in Chinese, verify logical accuracy and coding fluency, assess naturalness and correctness