Description: What do you need to know to join Topaz? Professional Experience * Experience in software development * Experience with data in activities related to MLOps or Data Science Technical Skills Python Programming: * Proficiency in Python for developing robust applications * Code versioning with Git * Solid knowledge of data structures, algorithms, and design patterns * Data manipulation with NumPy and Pandas * Model development with Scikit-Learn and TensorFlow * Unit testing with pytest * Load testing with Locust Cloud and Infrastructure: * Practical experience with AWS (EC2, S3, Lambda, ECR, ECS/EKS) * Containerization with Docker * Orchestration with Kubernetes * Infrastructure as Code with Terraform DevOps and CI/CD: * Experience with GitLab CI/CD for pipeline automation * Knowledge of DevOps practices applied to ML Databases: * Experience with NoSQL databases (MongoDB, DocumentDB, DynamoDB) * ORM model development for relational databases Preferred Qualifications * AWS certifications (Solutions Architect, Machine Learning Specialty) * Experience with MLOps tools (MLflow, Kubeflow, Airflow) * Knowledge of Feature Stores and Model Registry * Experience with model monitoring frameworks * Knowledge of data security and governance * Open-source contributions Your Day-to-Day at Topaz: At Topaz, you will be responsible for leading the development and deployment of advanced models that drive large-scale fraud prevention. Your day-to-day will be challenging and full of opportunities to apply your technical and strategic skills. Key responsibilities include: ML Development and Infrastructure * Develop and maintain automated ML pipelines (CI/CD) for model training, validation, and deployment * Adapt data transformation pipelines for machine learning model inference * Ensure scalability and availability of ML applications in production environments Production Deployment and Monitoring * Collaborate with Data Scientists to build robust and scalable pipelines * Implement continuous monitoring systems for model performance in production * Identify and mitigate performance degradation, data drift, and concept drift * Establish alerts and dashboards for tracking critical metrics Optimization and Continuous Maintenance * Implement strategies for automatic model retraining and versioning * Update models with new data while maintaining traceability and governance * Implement explainability techniques (XAI) to ensure transparency and regulatory compliance * Optimize infrastructure costs and processing time Research and Innovation * Explore and evaluate new technologies, frameworks, and MLOps tools * Contribute to defining best practices, technical standards, and team documentation * Stay up to date with trends and innovations in Machine Learning Operations 2512200202551929829