Senior ML Engineer, Real-Time Ranking & Personalization

Depop Limited - Nova; Greater London; Hybrid; GBP 90,000 - 120,000; Full time

Benefits offered by this job

Health & wellbeing

Cycle to Work

Employee Assistance Program

Life Insurance

Pension match

Dog-friendly offices

Job summary

Depop is seeking a Senior ML Engineer for the Ranking team in the UK to design, deploy and maintain production ML pipelines powering personalised rankings across search results and recommendations.

You will collaborate with ML Scientists, Backend Engineers and MLOps to build scalable ranking models, improve latency, observability and real-time serving, and help harden the ML infrastructure for ranking systems.

Qualifications

• Proven experience building and deploying ML pipelines in production.
• Experience with ranking, recommendation, or retrieval systems.
• Strong ML workflow knowledge from experimentation to production deployment.

Responsibilities

• Design pipelines for training, evaluating, deploying, and monitoring ranking models.
• Collaborate with ML scientists to productionise ranking models with reliability and observability.
• Build real-time model serving systems for personalised rankings across the app.
• Coordinate with backend/product teams for integration and deployment of ranking services.
• Extend ML infrastructure for ranking systems with CI/CD, feature store, monitoring and alerting.
• Maintain high standards for operational excellence, testing and incident response.
• Contribute to a culture focused on scalability, experimentation, and measurable impact.

Skills

ML pipelines

Ranking systems

Cloud environments

Ownership

Communication

AI curiosity

Tools

PyTorch

TensorFlow

scikit-learn

SageMaker

MLflow

TFServing

Spark

Databricks

AWS

Kafka

Airflow

Job description

Depop is seeking a Senior ML Engineer for the Ranking team in the UK to design, deploy and maintain production ML pipelines powering personalised rankings across search results and recommendations.

You will collaborate with ML Scientists, Backend Engineers and MLOps to build scalable ranking models, improve latency, observability and real-time serving, and help harden the ML infrastructure for ranking systems.