(Senior) ML Platform Engineer (w/m/d)

at  Billie

We are Billie, the leading provider of Buy Now, Pay Later (BNPL) payment methods for businesses, offering B2B companies innovative digital payment services and modern checkout solutions. We are to create a new standard for business payments and have made it our mission to simplify the purchasing experience for all businesses making it a tool for growth. Our solutions are based on proprietary, machine-learning-supported risk models, fully digitized processes and a highly scalable tech platform. This makes us a deep-tech company building financial products, not the other way around. We love building simple and elegant solutions and we strive for automation and scalability.

WHO WE ARE LOOKING FOR:

• You are familiar with data versioning and data governance practices
• You have an understanding of model versioning, reproducibility, and Experimentation using tools like MLflow or Weights & Biases
• You have experience with machine learning workflows and MLOps tools such as Metaflow and MLflow
• You have knowledge of model deployment, serving, and monitoring using tools like AWS SageMaker, KServe, Seldon Core
• You are familiar with model training and inference using popular frameworks like Scikit-learn or (optional) TensorFlow, PyTorch
• You are able to design and implement model deployment pipelines using Github Actions, ArgoCD or similar
• You have experience using orchestration tools such as Airflow, ArgoCD, Prefect.
• You are able to collaborate with data scientists to deploy, monitor, and optimize ML models in production

Billie is proud of having its decision engine, consisting of a combination of cutting-edge machine learning models and business logics, built internally. This engine is a core functionality of the product allowing Billie to evaluate Fraud and Risk propensity efficiently.
As a Senior MLOps Engineer, you will be responsible for designing, building, and maintaining scalable and resilient machine learning pipelines that support real-time and batch model deployment and monitoring. Your expertise in ML model lifecycle management, CI/CD for machine learning, and MLOps best practices will be key in supporting various AI and machine learning initiatives across the organization.

In this job you will:

• Design and implement a scalable and reliable ML platform: Develop robust ML pipelines for real-time and batch processing using tools such as MLflow, Kubeflow, Metaflow
• Ensure that ML model predictions are delivered reliably and timely and are continuously monitored for performance, accuracy, and reliability.
• Maintain and extend our inhouse batch and real-time feature platforms that power dozens of feature pipelines allowing timely data for model inference and reliable point in time accurate data for model training
• Collaborate with cross-functional teams: Work closely with data scientists and data engineers to understand model and feature requirements and translate them into scalable and reliable pipelines.
• Drive continuous improvement: Actively contribute to the team’s knowledge sharing, participate in tech talks, and drive architectural decisions as the subject matter expert (SME) in MLOps.
• Stay abreast of industry trends and advancements in MLOps technologies to improve our ML Platform