We are seeking a highly motivated and experienced Machine Learning Engineer to join our AI & Threat Analytics team. This is a 100% remote position with an opportunity to work a hybrid schedule for candidates based in the El Dorado Hills, CA or Chicago, IL metro area!
Keeper’s cybersecurity software is trusted by millions of people and thousands of organizations, globally. Keeper is published in 21 languages and is sold in over 120 countries. Join one of the fastest-growing cybersecurity companies and play a critical role in building Keeper's next-generation autofill and classification models in our browser extension.
About Keeper
Keeper Security is transforming cybersecurity for people and organizations around the world. Keeper’s affordable and easy-to-use solutions are built on a foundation of zero-trust and zero-knowledge security to protect every user on every device. Our award-winning, zero-trust, privileged access management platform deploys in minutes and seamlessly integrates with any tech stack and identity application to provide visibility, security, control, reporting and compliance across an entire enterprise. Trusted by millions of individuals and thousands of organizations, Keeper is an innovator of best-in-class password management, secrets management, privileged access, secure remote access and encrypted messaging. Learn more at KeeperSecurity.com.
About the Role
As a Machine Learning Engineer, you will develop advanced autofill systems, focusing on multi-lingual text classification of HTML input fields using state-of-the-art techniques such as autoencoders and fine-tuned language models. You’ll ensure that Keeper’s autofill features are fast, accurate, and intuitive, providing a seamless experience to millions of users globally. You’ll collaborate closely with cross-functional teams to implement and optimize high-performance models that elevate Keeper’s product offerings.
Responsibilities
- Design and implement ML models for real-time DOM structure and form-field detection.
- Fine-tune large language models for text classification, using projection layers and pooling.
- Build and optimize feature extraction pipelines for HTML attributes, DOM structures, relationships, and text-based features.
- Evaluate and fine-tune models using metrics like a confusion matrix, ROC/PR curves, and other techniques to optimize accuracy and performance.
- Deploy models in our browser extension to support client-side inference.
- Continuously improve model performance, accuracy, and runtime efficiency.
- Troubleshoot and optimize production models for consistency and reliability.
- Stay up-to-date with new ML frameworks (e.g., PyTorch, TensorFlow, Transformers) and incorporate improvements.
- Scale ML pipelines and experimentation systems to support millions of users.
- Collaborate with cross-functional teams to align ML efforts with product goals.
- Write clean, maintainable code and provide comprehensive documentation