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.

Bachelor’s degree in Computer Science, Engineering, Data Science, or a related field, or equivalent experience, with 5 years or equivalent of professional experience in machine learning or data science. MS or Ph.D is a plus.
Strong proficiency in Python and hands-on experience with ML frameworks such as PyTorch or TensorFlow.
Solid experience applying deep learning models (especially CNNs) in real-world computer vision systems, with working knowledge of transformer-based approaches.
Strong understanding of model evaluation, experimentation, and ML fundamentals, including overfitting, regularization, and transfer learning.
Experience with version control (Git), experiment tracking, and reproducible ML workflows.
Ability to communicate technical ideas clearly and work effectively in a cross-functional team.

Data Scientist II – Computer Vision

Key skills