AI Engineer II - Translation

Description Propio is on a mission to make communication accessible to everyone. As a leader in real-time interpretation and multilingual language services, we connect people with the information they need across language, culture, and modality. We're committed to building AI-powered tools to enhance interpreter workflows, automate multilingual insights, and scale communication quality across industries. We are seeking an AI Engineer II - Translation that will design and optimize machine learning solutions that enhance Propio's translation and localization capabilities, working closely with the translation team and the AI Engineers. This role focuses on developing neural machine translation models optimized for low-resource and specialized languages, improving post-editing workflows, and integrating AI seamlessly with linguist workflows to deliver faster and more accurate translations.

Key Responsibilities:

Design, train, and deploy neural machine translation (NMT) systems for multilingual scenarios, with emphasis on low-diffusion languages. Optimize models for low-resource and specialized domain languages, leveraging techniques like transfer learning and few-shot adaptation. Collaborate with the LLM AI Engineer to integrate large language models into translation pipelines and compare approaches for different language pairs. Develop post-editing and quality assurance tools to augment human translators, incorporating human-in-the-loop feedback. Work closely with linguists, product managers, and engineers to integrate AI into translation pipelines and gather domain feedback. Continuously evaluate and benchmark model performance using standardized metrics (BLEU, COMET) and custom domain-specific metrics. Stay current with research advancements in multilingual NLP and low-resource translation techniques.

Requirements Qualifications:

Bachelor's or Master's degree in Computer Science, Computational Linguistics, Statistics, or related field. Strong background in NLP and machine translation systems. Proven experience optimizing models for low-resource or underrepresented languages. Proficiency in Python and ML frameworks (PyTorch, TensorFlow, Hugging Face). Experience with multilingual datasets, translation quality evaluation, and human feedback incorporation.

Preferred Qualifications:

Prior work in translation, interpretation, summarization, or cross-lingual QA Contributions to open-source NLP projects and translation quality projects Experience working with speech-to-text pipelines or multimodal systems #LI-JS1