Machine Learning Engineer, Search and Ranking Systems

WHAT YOU'LL DO

• Design, build, and deploy robust, end-to-end MLOps pipelines on Databricks for complex models, including NLP and multimodal systems.
• Architect and manage large-scale data flows using PySpark, pulling from diverse sources like Azure Data Lake Storage (ADLS) and Google BigQuery to fuel our model training and inference services.
• Develop and maintain scalable APIs and services that can handle millions of requests daily to serve model predictions, ensuring high availability and low latency.
• Champion engineering best practices by writing clean, tested, and maintainable code, and developing reusable libraries and frameworks that accelerate the team's delivery.
• Implement comprehensive monitoring and alerting for model performance and data drift to ensure our systems remain accurate and reliable over time.

WHO YOU ARE

• A skilled software engineer with a passion for machine learning. You have proven experience building and deploying end-to-end ML-powered products in a production environment.
• Proficient in Python and modern software engineering practices, including version control (Git), CI/CD, dependency management, and automated testing.
• Experienced with distributed data processing. You have hands-on experience writing and optimizing complex data pipelines using Spark/PySpark.
• Comfortable in a cloud-native environment. You have practical experience with a major cloud platform (Azure, GCP, or AWS) and its data services.
• An excellent collaborator and communicator, able to work effectively in a cross-functional team of technical and non-technical members.
• Nice to have:
• Deep expertise with the Databricks platform, including Delta Lake, MLflow, and model serving.
• Experience with containerization technologies like Docker and orchestration with Kubernetes.
• Experience with Redis, particularly in high-throughput caching or as a low-latency feature store.
• Experience with Apache Airflow or similar workflow orchestration tools for managing complex data and machine learning pipelines.
• Experience with monitoring and logging frameworks (Grafana, Prometheus).

REWARDS & BENEFITS

• Health insurance for the whole family, flexible working environment and well-being support and tools
• Extra days off, sabbatical program and days for you to give back for the community
• Training opportunities and free access to Udemy
• Flexible benefits program

EQUAL OPPORTUNITIES STATEMENT

• Farfetch is an equal opportunities employer ensuring that all applicants are treated equally and fairly throughout our recruitment process. We are determined that no applicant experiences discrimination on the basis of sex, race, ethnicity, religion or belief, disability, age, gender identity, ancestry, sexual orientation, veteran status, marriage and civil partnership, pregnancy and maternity, or any other basis prohibited by applicable law.

SCAM DISCLAIMER

• It has come to our attention that there may be fraudulent activities involving individuals or organizations falsely claiming to represent Farfetch in order to attract candidates to a SCAM. Please be aware that Farfetch does not conduct recruitment processes through messaging apps or any unofficial communication channels, other than our official careers website. Additionally, Farfetch will never ask candidates for any form of payment during the recruitment process.