Senior Machine Learning Engineer - Recommendations (Core)

In this role you will design and ship ML models for recommendations and related problems, advancing SoundCloud's personalization capabilities. You will help modernize our stack by migrating models to PyTorch-based GPU pipelines and ensure models perform well in production. You’ll work with cross-functional teams to bring offline gains online, shaping how artists connect with communities and how listeners discover music. This is a hands-on, impact-driven position at a fast-moving team focused on scalable, high-quality recommendations.

• Design, train and ship models for recommendations (candidate generation, user/item modeling, ranking) and related problems in search and content understanding
• Lead the migration of models from classical methods to PyTorch-based, GPU-powered pipelines
• Adapt, fine-tune and evaluate open-source embedding and ranking models for catalog use cases
• Own end-to-end evaluation: offline metrics, A/B tests, ensuring offline gains translate online
• Collaborate with ML, data and backend engineers to deploy models to production and set modeling standards across the team

• 3+ years building ML systems in production with end-to-end ownership of at least one ranking, retrieval or recommendation model
• Strong deep learning skills in PyTorch (or similar) and solid grasp of embeddings, two-tower models, learning to rank, multi-objective ranking
• Experience with evaluation and experimentation for ranking systems, including biases in implicit feedback (clicks, plays)
• Strong Python; experience with large-scale data processing (Spark/BigQuery) and deploying models on cloud platforms (GCP preferred)
• M.Sc. in a quantitative field or equivalent experience

• PyTorch
• embeddings
• two-tower models
• learning to rank
• multi-objective ranking
• biases in implicit feedback