Senior Machine Learning Engineer

About the Role

Our mission on the Advertising Product & Technology team at Spotify is to build a next-generation advertising platform that aligns with our unique value proposition for audio and video. We work to scale the user experience for hundreds of millions of fans and hundreds of thousands of advertisers. This scale brings unique challenges as well as tremendous opportunities for our artists and creators.

We are seeking a Senior Machine Learning Engineer to join the Ad Engagement squad. Ad Engagement focuses on using machine learning to accurately predict how Spotify listeners will react to ads, helping advertisers minimize their costs while delivering a more relevant and enjoyable ad experience for listeners. Our core innovations include Multi-Task Learning models (MTL), and we are expanding into scalable sequence modeling with complex transformer architectures. Recently, we presented a paper about this in KDD Toronto and you can check out the latest details in the blog post here.

We are also seeking a Senior Machine Learning Engineer to join the Supply Personalization squad. Supply Personalization focuses on optimizing the volume, timing, and types of ad loads a user receives. By leveraging data, machine learning, causal inference, and large scale online experimentation, we aim to uncover and learn the most effective strategies for enhancing user experiences and driving business outcomes.

We are looking for someone with strong expertise in data analysis, online experimentation techniques, and large-scale ML and engineering systems; someone who is motivated by user and business problems as much as they are by technical problems, and who thrives under ambiguity, experimentation, and iteration. You will work directly on an array of product features that drive the optimal user experience for our ads. You will collaborate with our cross-functional teams to ideate, develop, and own complex technical solutions on our ad services technology platforms. As someone who shares our passion for building innovative ad experiences, you'll have a direct impact on how the world uses Spotify.

What You'll Do

• Design and implement machine learning systems for ad performance optimization.
• Research and apply ML optimization strategies to balance multiple objectives effectively.
• Work on a paradigm shift modeling work for Ads that involves working on Sequence Transformer model for User-Ad Interaction, that works along a MTL model.
• Analyze data and use machine learning techniques to understand user behavior and improve ad experiences.
• Collaborate with backend engineers, data scientists, data engineers, and product managers to establish baselines, inform product decisions, and develop new technologies.

Who You Are

• You have professional experience in applied machine learning.
• You have strong technical expertise in software engineering, data analysis, and machine learning.
• You are proficient in programming languages such as Python, Java, or Scala.
• Experienced in Tensorflow or PyTorch and working with various aspects of the ML lifecycle.
• You have expertise in developing data pipelines using tools like Apache Beam or Spark.
• As a plus, you may have experience with any of the following - LLMs, Ray, Adtech, or Recommender Systems.

Where You'll Be

We offer you the flexibility to work where you work best! For this role, you can be within the Americas region as long as we have a work location. This team operates within the U.S. Eastern time zone for collaboration.

The United States base range for this position is $184,050.00 - $262,928.00, plus equity. The benefits available for this position include health insurance, six-month paid parental leave, 401(k) retirement plan, monthly meal allowance, 23 paid days off, 13 paid flexible holidays, paid sick leave. This range encompasses multiple levels. Leveling is determined during the interview process. Placement in a level depends on relevant work history and interview performance. These ranges may be modified in the future.

Key Skills/Competency

• Machine Learning
• Deep Learning
• Python
• Java
• Scala
• TensorFlow
• PyTorch
• Data Analysis
• Apache Spark
• Apache Beam
• Adtech
• Recommender Systems
• Multi-Task Learning
• Transformer Architectures
• Causal Inference
• Online Experimentation