Senior Machine Learning Engineer – Voice Personalization

Spotify

  • Full Time

The Personalization team makes deciding what to play next easier and more enjoyable for every listener. From Blend to Discover Weekly, we’re behind some of Spotify’s most-loved features. We built them by understanding the world of music and podcasts better than anyone else. Join us and you’ll keep millions of users listening by making great recommendations to each and every one of them. We ask that our team members be physically located in Central European time or Eastern Standard/Daylight time zones for the purposes of our collaboration hours.

Voice is quickly becoming the interaction modality of choice for everything from your phone to smart speaker to car. But have you ever wondered what happens between you speaking and magically starting on the perfect audio journey, whether with your favorite artist or podcaster? At Spotify Voice, we are responsible for making sure that Spotify listeners get what they’re asking for, no matter whether they ask for it via the “Hey, Spotify” wakeword, on our amazing Car Thing in-car voice-powered audio player, on a home speaker via Alexa or Google, or on their phone via Siri, Google, or Samsung Bixby. We make sure to properly understand what the user said via state-of-the-art Natural Language Processing techniques, apply arbitration and routing logic between possible fulfillment paths, and plug into Spotify’s world-class search indexing and retrieval system to find the perfect content among hundreds of millions of tracks, playlists, podcasts, and other audio content. 

We are looking for a Senior ML Engineer to join the Spotify Voice family. We want somebody who can dive into the world of NLU and NLP models, leverage intelligent data annotation and sampling techniques, integrate with search retrieval and ranking systems, and apply modern techniques leveraging multiple models and data sources for optimizing the user experience via targeted experimentation. You will be working with a multi-functional team of impactful linguists, ML NLU/NLP experts, as well as data and backend engineers. The team is spread across Boston, New York, and Stockholm, with remote contributors from across the US. We are looking for somebody with broad ML expertise, strong production experience, and a respect for solid engineering practices to join the team and help us build and scale for the next decade in Voice. If this sounds interesting to you, and you’re ready to join a team that values communication, humility, and a growth mindset, then come join us and you’ll keep millions of users listening to excellent audio recommendations every day, on their phone, in the car, and at home!

 

What You’ll Do

 

  • Contribute to designing, building, evaluating, shipping, and refining Spotify’s personalization products through hands-on ML development
  • Collaborate with a multi-functional agile team spanning data engineers, applied ML engineers, software engineers, data/content analysts, research scientists, user researchers, designers, and product managers to build new product features that advance our mission to connect artists and fans in personalized and relevant ways
  • Prototype new approaches and productionize solutions at scale for our hundreds of millions of active users
  • Lead by example in terms of code consistency, performance, robustness, and scalability
  • Perform data analysis to establish baselines and inform product decisions
  • Drive optimization, testing, and tooling development to improve quality
  • Be part of an active group of machine learning practitioners across Spotify
  •  

    Who You Are

     

  • You have an MSc or PhD in Computer Science, Machine Learning, Engineering, Mathematics, Physics, Computational Linguistics, or equivalent
  • You are a technical expert with a deep understanding of machine learning theory and practice, with production experience with ML algorithms for ranking and recommendation systems and Natural Language Processing applications such as parsing and text classification
  • You have 5+ years of professional engineering experience working in a product-driven environment implementing machine learning systems at scale in Java, Scala, Python, C++, or similar languages, with experience with TensorFlow and the TensorFlow ecosystem (TFX) a big plus
  • You understand the data annotation pipeline from data selection to aligning labeling efforts to ML model improvements, have experience with architecting data pipelines, and are self-sufficient in getting the data you need to build and evaluate your models, preferably using tools like Apache Beam or Spark, Scio, and cloud platforms like GCP or AWS
  • You care about and are able to engage in agile software processes, data-driven development, reliability, and disciplined experimentation
  • You have excellent communication skills and the ability to collaborate with team members across all job functions
  • You enjoy surveying research publications in the machine learning and software engineering communities
  • You love your customers even more than your code
  •  

    Where You’ll Be

     

  • We are a distributed workforce enabling our band members to find a work mode that is best for them!
  • Where in the world? For this role, it can be within the Americas or EMEA region
  • Prefer an office or prefer working from home instead? Not a problem! We have plenty of options for your working preferences. Find more information about our Work From Anywhere options here
  • Working hours? We operate within the Eastern Standard time zone for collaboration. Limited exceptions will be made for other US time zones, Greenwich Mean, and Central European time zones
  •  

     

     

    Spotify is an equal opportunity employer. You are welcome at Spotify for who you are, no matter where you come from, what you look like, or what’s playing in your headphones. Our platform is for everyone, and so is our workplace. The more voices we have represented and amplified in our business, the more we will all thrive, contribute, and be forward-thinking! So bring us your personal experience, your perspectives, and your background. It’s in our differences that we will find the power to keep revolutionizing the way the world listens.
    Spotify transformed music listening forever when we launched in 2008. Our mission is to unlock the potential of human creativity by giving a million creative artists the opportunity to live off their art and billions of fans the chance to enjoy and be passionate about these creators. Everything we do is driven by our love for music and podcasting. Today, we are the world’s most popular audio streaming subscription service.
    Global COVID and Vaccination Disclosure
    Spotify is committed to safety and well-being of our employees, vendors and clients. We are following regional guidelines mandating vaccination and testing requirements, including those requiring vaccinations and testing for in-person roles and event attendance. For the US, we have mandated that all employees and contractors be fully vaccinated in order to work in our offices and externally with any third-parties. For all other locations, we strongly encourage our employees to get vaccinated and also follow local COVID and safety protocols.