Stripe
Machine Learning Engineer, Identity
Stripe - San Francisco, California, United States, 94199
Work at Stripe
Overview
- View job
Overview
Before Stripe, every growing internet platform had a payments team. Today, every growing internet platform has an Identity team. Identity verification is a core piece of economic infrastructure for online businesses. Great identity solutions can help platforms automate the process of satisfying regulatory obligations while keeping their users safe. Join Stripe to help build a service that empowers platforms to take the burden and cost out of identity verifications and scale globally with ease.
We’re looking for a Machine Learning engineer to help envision, build, and deploy novel approaches for using optical character recognition (OCR) on identity documents while maintaining a great user experience. This role is perfect for engineers interested in using computer vision and machine learning algorithms to build state-of-the-art OCR solutions.
You will: Define and drive the vision for OCR practice for Stripe’s Identity product Design and deploy new OCR algorithms using tools such as Tensorflow, PyTorch, OpenCV, etc. Design systems for text detection and extraction, document layout recognition, and language detection Iteratively improve document detection and extraction models Explore green-field projects and convert abstract requirements into concrete deliverables Improve the way we evaluate and monitor our model and system performance Collaborate with stakeholders and drive projects involving a wide variety of technologies and systems to successful completion We’re looking for someone who has: An advanced degree in a quantitative field (e.g. statistics, mathematics, computer science) and experience in software engineering in a production environment 5+ years industry experience working on end-to-end OCR systems Experience designing computer vision algorithms and training machine learning models to solve text detection and recognition, document layout recognition, and language detection problems Knowledge about how to manipulate data to perform analysis, including querying data, defining metrics, or slicing and dicing data to evaluate a hypothesis Nice to have: previous experience or interest in identity verification products
We’re looking for a Machine Learning engineer to help envision, build, and deploy novel approaches for using optical character recognition (OCR) on identity documents while maintaining a great user experience. This role is perfect for engineers interested in using computer vision and machine learning algorithms to build state-of-the-art OCR solutions.
You will: Define and drive the vision for OCR practice for Stripe’s Identity product Design and deploy new OCR algorithms using tools such as Tensorflow, PyTorch, OpenCV, etc. Design systems for text detection and extraction, document layout recognition, and language detection Iteratively improve document detection and extraction models Explore green-field projects and convert abstract requirements into concrete deliverables Improve the way we evaluate and monitor our model and system performance Collaborate with stakeholders and drive projects involving a wide variety of technologies and systems to successful completion We’re looking for someone who has: An advanced degree in a quantitative field (e.g. statistics, mathematics, computer science) and experience in software engineering in a production environment 5+ years industry experience working on end-to-end OCR systems Experience designing computer vision algorithms and training machine learning models to solve text detection and recognition, document layout recognition, and language detection problems Knowledge about how to manipulate data to perform analysis, including querying data, defining metrics, or slicing and dicing data to evaluate a hypothesis Nice to have: previous experience or interest in identity verification products