Senior Machine Learning Engineer

This is a fully remote position, open to applicants in California.

📋 Description

• Construct, train, and enhance computer vision models for tasks such as image classification, face liveness detection, and presentation attack detection (PAD) / anti-spoofing.

• Address real-world identity verification and biometric authentication challenges, enhancing model performance against noisy and adversarial inputs like spoofed images, replay attacks, deepfakes, and synthetic media.

• Design and execute experiments aimed at boosting model accuracy, recall, robustness, and fraud detection efficacy through various techniques, including augmentation, class balancing, architecture tuning, and hard-negative mining.

• Create, train, and refine deep learning models (e.g., CNNs, Vision Transformers, and foundation models), focusing on loss function design, hyperparameter optimization, and performance tuning on extensive image datasets.

• Prepare and curate large, noisy datasets, encompassing data ingestion, validation, cleaning, deduplication, labeling strategies, and dataset quality assurance to enhance model reliability and generalization.

• Develop evaluation protocols and success metrics that balance fraud detection effectiveness with false acceptance rates, false rejection rates, and overall business impact.

• Create production-grade training and inference pipelines on AWS, ensuring strong reproducibility, monitoring, observability, and cost management.

• Transform models into robust Python services and libraries; collaborate with platform teams to optimize APIs, latency, scalability, and operational reliability.

• Contribute to the advancement of our Identity Verification (IDV) platform by modernizing legacy components and enhancing model performance, maintainability, and modularity.

• Collaborate closely with Product, Customer Success, Fraud, and Platform Engineering teams to guarantee that ML solutions comply with privacy, security, compliance, and reliability standards.

• Provide support and mentorship to other engineers through design reviews, code reviews, best practices in experimentation, and knowledge sharing.

• Investigate and assess emerging techniques in face liveness detection, presentation attack detection (PAD), deepfake detection, biometric authentication, and adversarial machine learning to bolster our fraud prevention capabilities.

⛳️ Requirements

• Bachelor's degree in Computer Science, Electrical Engineering, Computer Engineering, or a related technical field (or equivalent professional experience).

• Over 5 years of experience in applied machine learning, computer vision, or ML engineering with a solid foundation in software engineering (or an equivalent combination of education and experience).

• Proficient in Python programming with experience in building production-quality machine learning systems.

• Experience in developing and deploying computer vision models for image classification, detection, segmentation, or similar image-based learning tasks in production settings.

• Practical experience in designing, training, evaluating, and optimizing deep learning models using frameworks like PyTorch or TensorFlow.

• Strong background in computer vision, including familiarity with CNNs, Vision Transformers, foundation models, image processing, and feature extraction techniques.

• Experience handling large-scale image datasets, including data preprocessing, augmentation, labeling strategies, dataset quality assurance, and model evaluation.

• Comprehension of model performance trade-offs, including precision, recall, false positive rates, false negative rates, and robustness in real-world conditions.

• Demonstrated ability to build reliable training and inference pipelines and collaborate on the production deployment of machine learning systems.

• Excellent communication and collaboration skills, enabling effective teamwork across engineering, product, fraud, operations, and platform teams.

• Experience in evaluating and enhancing model performance under adversarial, noisy, or highly imbalanced datasets.

🏝️ Benefits

• Wellness: Options for universal, supplemental, and private healthcare plans based on country specifics.

• Financial future: Contributions to retirement/pension plans and participation in the MTK stock plan.

• Income protection: Coverage for life events and disabilities.

• Paid time off: Generous annual leave, company holidays, and volunteer time off.

• Learning: Access to e-learning licenses, tuition reimbursement, and hackathons.

• Home office setup allowance.

• Additional/optional benefits: Pet insurance, identity theft protection, and legal assistance.