Machine Learning Engineer - III (Fraud)

Role Purpose

Role Value

Key Responsibilities

• Design, develop, and deploy production-grade machine learning and deep learning models for data extraction and ID verification tasks.
• Apply a deep understanding of fundamental ML concepts such as overfitting, regularization, ROC curves, loss functions, precision, and recall to design robust ML systems.
• Conduct model robustness assessment, validation, and adversarial testing to ensure real-world performance reliability.
• Build, train, and optimize models using PyTorch and TensorFlow frameworks.
• Own the end-to-end model lifecycle from experimentation and evaluation to deployment (e.g., AWS SageMaker endpoints or on-device inference).
• Develop high-quality, maintainable Python code for ML pipelines and adhere to best practices for monitoring and maintaining models in production.
• Stay current with emerging research, techniques, and tools in machine learning and computer vision.
• Collaborate closely with engineers, product managers, and data scientists in an Agile development environment.

Experience and Qualifications

• Bachelor s or Master s degree in Computer Science, Machine Learning, Data Science, or a related field.
• 5+ years of hands-on experience developing and deploying machine learning or deep learning models in production environments.
• Excellent Python programming skills and proficiency with ML libraries such as PyTorch, TensorFlow.
• Strong understanding of core ML principles overfitting, regularisation, ROC analysis, loss optimization, and precision-recall tradeoffs.
• Proven experience in deploying, monitoring, and maintaining models in production environments (not research-only or lab setups).
• Experience performing robustness assessments and adversarial testing on ML models.

Nice to Have

• PhD in Computer Science or related field with a focus on machine learning or related field.
• Familiarity with AWS or GCP cloud environments and large-scale ML model deployment.
• Understanding of Spring/Java-based system architectures is advantageous.

Jumio Values

@Work

About Jumio

Equal Opportunities