Machine Learning Engineering Intern, Recommendation Systems

Role overview

Support the development of recommendation systems that help people discover music and engage with creators. The internship spans applied machine learning and software engineering, from preparing interaction data and testing models to building prototypes and evaluating how well recommendations work.

Responsibilities

- Implement and experiment with models for personalized recommendations, content discovery, and ranking. - Process datasets, extract useful features, and prepare data for training and evaluation. - Train, benchmark, and compare recommendation approaches, documenting findings and potential improvements. - Turn algorithms and research ideas into working prototypes using Python and machine learning frameworks. - Work with engineering and product colleagues to test approaches and improve recommendation systems.

Requirements

- Currently pursuing a bachelor's, master's, or doctoral degree in computer science, machine learning, data science, statistics, or a related field. - Strong Python programming skills and familiarity with NumPy and pandas. - Foundational knowledge of machine learning, statistics, and data analysis. - Practical experience with at least one machine learning framework; PyTorch is preferred. - Interest in recommendation systems, information retrieval, ranking, or personalization. - Curiosity, problem-solving skills, and willingness to learn and collaborate.

Nice to have

- Academic or personal projects involving machine learning or recommendation systems. - Familiarity with collaborative filtering, content-based methods, embeddings, or model evaluation. - Experience with SQL, real-world datasets, or user interaction data. - Interest in music discovery or social platforms.

Benefits and work setup

The internship offers hands-on experience across the machine learning lifecycle, from data preparation and model development through evaluation and product integration. Interns collaborate with engineering, research, and product colleagues, receive mentorship, and can experiment with different recommendation approaches and architectures.