Senior Machine Learning Engineer

This is Adyen At Adyen, we’re engineered for ambition. We empower our teams with the culture and support they need to own their careers. The people of Adyen are motivated problem-solvers who tackle unique technical challenges at scale, delivering innovative and ethical solutions to help businesses achieve their ambitions faster. For our teams, we create an environment with opportunities for our people to succeed, backed by the culture and support to ensure they are enabled to truly own their careers. We are motivated individuals who tackle unique technical challenges at scale and solve them as a team. Together, we deliver innovative and ethical solutions that help businesses achieve their ambitions faster. Machine Learning Engineer Adyen is looking for a Senior Machine Learning Engineers to join our team in Amsterdam, someone with experience of building and operating robust machine learning systems at scale in production environments. You will be responsible for designing, productionizing and maintaining machine learning services that power data products at Adyen. In this role, you will:  Develop and maintain production ML pipelines for data ingestion, training, validation, and deployment. Examples ML domains are: on-line learning algorithms to pick the best optimization decision in a changing environment, clustering algorithms to group customers/shoppers, supervised and semi-supervised learning methods for inference on risk patterns or graph analysis, representation learning for behavior prediction and monitoring, Anti-Money Laundering (AML) systems and real-time anomaly detection based on time-series modeling; Identify and fix performance bottlenecks in ML training and inference (memory consumption, online latency, training time etc.); Collaborate with software engineers to integrate ML solutions into products and services; Collaborate with data scientists to transition research prototypes into scalable solutions; Collaborate with MLOps and platform teams to integrate effectively with current tools, and shape priority for future tools; Support and encourage good engineering practices on product ML teams; Who You Are: You have 5 + years of experience as an engineer working in the machine learning domain; 5 years of experience with one or more general purpose programming languages including but not limited to: Java, C/C++ or Python. 5 years of experience in software development. 5 years of experience testing, and launching software products, and 3 years of experience with software design and architecture. 5 years of experience building and deploying Machine Learning systems in (prediction, ranking, embedding, deep learning) in production and experience building architecture in different modeling domains. 5 years of experience with ML design and ML infrastructure (e.g., model deployment, model evaluation, data processing, debugging, fine tuning). You have experience leveraging big data to create the pipelines needed to feed the models with appropriate data; You have a strong understanding of good software engineering practices as well as data engineering and MLOps principles; You have strong familiarity with the standard data science toolkit in python, such as (py)spark, (Trino) SQL, Tensorflow, PyTorch, XGBoost/LightGBM, Pandas, MLFlow or similar MLOps frameworks, and Airflow; You have knowledge/experience of working with ML infrastructure components with tools such as k8s, docker, airflow, argo-workflows, prometheus, grafana You have an experimental mindset with a launch fast and iterate mentality; You proactively take the lead in projects, from ideation to deployment. You have experience working with a wide range of stakeholders and can clearly communicate complex outcomes over a wide range of audiences. Nice to Have: You have experience with distributed GPU compute environments You have experience working with a Machine Learning ‘Feature Store’ Teams currently hiring: Customer Risk The Customer Risk team is at the front line of this platform, building the next-generation systems required to assess and mitigate risk in real time. They are responsible