• Develop, maintain, and improve machine learning models for document verification use cases such as document classification, image quality assessment, field extraction, and fraud detection. • Independently implement and evaluate deep learning architectures, including CNNs and transformer-based vision or multimodal models. • Own well-defined components of end-to-end ML pipelines, including data preparation, model training, evaluation, and deployment to production. • Perform in-depth error analysis, model diagnostics, and performance optimization, and propose data- or model-driven improvements. • Contribute to technical design discussions, code reviews, and modeling best practices across the team. • Write production-quality, maintainable code and contribute to shared ML tooling and infrastructure. • Collaborate with engineering and product partners to ensure models meet product, performance, and reliability requirements.