Machine Learning Engineer 3

Develop and own end-to-end machine learning models, including custom transformer-based architectures, to detect fraud, prevent account sharing, and protect user experience.

Manage full ML lifecycle: data preprocessing, feature engineering, model architecture design, large-scale GPU training, production deployment, and ongoing monitoring.

Optimize model training and inference efficiency on distributed GPU infrastructure and contribute to MLOps practices such as experiment tracking, versioning, CI/CD, and automated retraining.

Bachelor’s or Master’s degree (or equivalent experience) in Computer Science, Machine Learning, Data Science, or related field.

5+ years of professional experience building and deploying machine learning solutions at scale.

Strong programming skills in Python with hands-on experience in PyTorch or TensorFlow frameworks.

Deep understanding of end-to-end machine learning lifecycle and expertise in model optimization and production system integration.

Experience with deep learning models involving custom transformers and attention mechanisms for long sequential behavioral data.

Familiarity with large-scale GPU training optimizations such as mixed-precision training, gradient checkpointing, and distributed training strategies (DDP, FSDP).

Prior work in fraud detection, anomaly detection, or behavioral modeling domains is a strong advantage.