Senior ML Engineer, Disputes Platform & MLOps

Checkout Ltd; Greater London; On-site; GBP 90,000 - 130,000; Full time

Job summary

Checkout.com in London is seeking an experienced ML Engineer to join the Disputes ML team and help build our new ML-driven dispute optimisation suite. You will work on end-to-end features from data pipelines to model deployment, collaborating with platform and backend engineers to scale production systems.

Applicants should have 5+ years in ML/MLOps, strong Python, Databricks experience, and familiarity with AWS or Azure.

Qualifications

• 5+ years of experience in ML/MLOps or ML engineering.
• Proficient Python with production-quality code.
• Experience with production ML models (online or offline) and MLOps practices.
• Experience with monitoring and observability of production systems.
• Experience with training and operating models on Databricks.
• Familiarity with cloud-based application development (AWS & Azure).
• Familiarity with ML frameworks: scikit-learn, xgboost, TensorFlow, PyTorch, Spark, SageMaker, Vertex AI, Kubeflow, Seldon, Triton.

Responsibilities

• Build systems for training, deploying and monitoring ML models at scale for the Disputes platform.
• Develop and optimise data pipelines and backend services to process dispute and payment data in real time.
• Scale our feature store for online and offline use-cases.
• Own end-to-end feature delivery from requirements to production deployment.
• Turn raw data into production-ready features for dispute systems.
• Collaborate with platform and backend engineers to integrate models seamlessly.

Skills

Python

MLOps

Model training

Data pipelines

Feature store

Observability

Tools

Databricks

AWS

Azure

Spark

Kubeflow

Seldon

Job description

Checkout.com in London is seeking an experienced ML Engineer to join the Disputes ML team and help build our new ML-driven dispute optimisation suite. You will work on end-to-end features from data pipelines to model deployment, collaborating with platform and backend engineers to scale production systems.

Applicants should have 5+ years in ML/MLOps, strong Python, Databricks experience, and familiarity with AWS or Azure.