Senior Machine Learning Engineer

Role

Depop is looking for a dedicated Machine Learning Engineer to join our new Core ML team in the UK. You will work alongside ML Scientists, Backend Engineers, and MLOps to build, deploy, maintain, and monitor machine learning infrastructure, such as product matching pipelines, image embedding services, and lightweight classifier deployments, that support multiple product and marketing use cases across Depop.

Responsibilities

You will:

• Design and implement pipelines for training, deploying, and monitoring real-time and batch ML models

• Work closely with ML Scientists to productionise models and improve reliability, latency, and observability

• Partner with backend and product teams across Depop to define integration requirements and coordinate deployments of shared ML components

• Help design and extend the ML platform at Depop in collaboration with the MLOps team, across areas such as:

  • Robust prototyping and training workflows

  • CI/CD for model deployment

  • Real-time and batch model serving

  • Online/offline feature consistency via our feature store

  • Monitoring and alerting

• Hold high standards for operational excellence, including testing, monitoring, maintainability, and incident response

• Contribute to a strong ML engineering culture focused on scalability, collaboration, and continuous learning

Required Skills and Experience

• Proven track record of building and deploying ML pipelines and contributing to ML platform tooling

• Solid understanding of ML workflows and experience supporting scientists through to production

• Strong ownership mindset and ability to work independently

• Excellent communication skills across technical and non-technical stakeholders

• Experience designing systems in modern cloud environments (e.g. AWS, GCP)

Technologies and Tools

• Python

• ML and MLOps tooling (e.g. SageMaker, Databricks, TFServing, MLflow)

• Common ML libraries (e.g. scikit-learn, PyTorch, TensorFlow)

• Spark and Databricks

• AWS services (e.g. IAM, S3, Redis, ECS)

• Shell scripting and related developer tooling

• CI/CD tools and best practices

• Streaming and batch data systems (e.g. Kafka, Airflow, RabbitMQ)