2 months ago
Remote, IndiaStaff+
Responsibilities
- Develop, maintain, and own key computer vision fraud models that shape Jumio’s fraud product offering.
- Design and implement machine learning, deep learning, and classical computer vision solutions for fraud detection.
- Conduct research supporting the deployment of advanced algorithms.
- Deploy models as AWS SageMaker endpoints or directly onto devices.
- Monitor and maintain production ML models and stay current with advances through academic papers and industry conferences.
- Collaborate with engineers and product managers in an Agile development environment.
Requirements
- Bachelor’s or Master’s degree in Computer Science, Data Science, Machine Learning, or a related field.
- At least 6 years of commercial machine learning or deep learning experience, excluding time spent studying.
- Experience training deep learning models for deepfake, synthetic data, or generative AI data detection.
- Strong understanding of converting ML metrics into product goals.
- Hands-on experience with PyTorch or TensorFlow, scikit-learn, and production-grade Python development.
- Demonstrated experience applying best practices for monitoring and maintaining ML models in production.
- Strong communication and problem-solving skills.
- Preferred experience includes working with LLMs or VLMs, image or video generation, AWS or GCP cloud environments, and global organizations across multiple time zones.
Tech Stack
Categories
About Jumio
Jumio builds identity verification, document verification, and KYC solutions for enterprises, delivered via APIs and web workflows to reduce fraud and meet compliance. Privately held and founded in 2015 with headquarters in Jaipur, India, it verifies government-issued IDs and biometrics with liveness checks from 200+ countries, serving sectors such as financial services, fintech, e-commerce, and online gaming.