AI/ML - Machine Learning Engineer, Text Language Identification
Core
Build next-generation text language identification systems that detect and classify languages across diverse scripts, regions, and user contexts to power multilingual features like translation, search, and content recommendation.
Role type
Senior IC machine learning engineer (NLP)
Builds
Production text language identification models and multilingual data pipelines
Domain
Natural Language Processing (NLP) / Multilingual Systems
Deliverable
production ML models
Required skills
Neural model training and evaluation, Python programming, Deep learning frameworks (PyTorch, TensorFlow, JAX), Multilingual dataset curation, Transfer learning, Multilingual pretraining, Data augmentation, Model optimization (quantization, pruning, distillation), Lightweight model architecture design, Edge deployment strategies
Preferred skills
Text classification, Language identification, Dialect identification, Embedding models, Sentence representations, Contrastive learning, Hugging Face ecosystem (transformers, tokenizers, datasets), Low-resource language handling, Code-switching handling, Mixed-language input handling, Model versioning and reproducibility