LILT is seeking multilingual software engineers to help build and verify a rigorous Terminal-Bench evaluation suite. You will craft task environments, translate prompts, and develop deterministic verifier scripts to test model robustness across languages.
As an independent contractor, you’ll work with a diverse, general team, setting your own schedule. You will engage in 4-layer quality control and contribute to cutting-edge language technology research.
📌 Remote AI Benchmark Engineer (Perú)
🏢 Lilt Ai
📍 Perú