AI Benchmark Engineer | Native Language Specialist - German (Switzerland) - Remote

As an AI Benchmark Engineer | Native Language Specialist you will help Lilt evaluate its translation models on Swiss‑German data, turning raw benchmark results into clear, actionable insights for product teams. You will work each day with data scientists, linguists and engineers to assemble high‑quality test corpora, build automated evaluation pipelines and document performance trends in data‑driven reports. The role demands a native‑level command of Swiss German, solid experience with NLP evaluation metrics such as BLEU or COMET, and strong Python skills (pandas, NumPy, PyTorch/TensorFlow). A background in computational linguistics, machine translation or a related discipline, together with proven analytical and communication abilities and experience handling large linguistic datasets, is essential. The position is fully remote, part of a globally distributed, research‑focused team shaping cutting‑edge AI translation technology. What the role asks for: - Native‑level German (Swiss variant) - Experience with NLP evaluation metrics (BLEU, COMET, etc.) - Proficiency in Python (pandas, NumPy, PyTorch/TensorFlow) - Background in computational linguistics or machine translation - Strong analytical skills - Strong communication skills - Experience with large linguistic datasets