The Personalization team makes deciding what to play next on Spotify easier and more enjoyable for every listener. We seek to understand the world of music and podcasts better than anyone else so that we can make great recommendations to every individual person and keep the world listening. Every day, hundreds of millions of people all over the world use the products we build which include destinations like “Home” and “Search” as well as original playlists such as “Discover Weekly” and “Daily Mix.” We’re a team of technologists, product insight experts, designers, and product managers in Boston, New York, Stockholm, and London.
The Spotify Personalization Voice team is looking for an Analytical Linguist to join our team! We are seeking a candidate with strong linguistics foundations, strong analytical skills, and language technology experience, to help us develop language components for integration across a number of devices and customer experiences.
What you’ll learn and do
– Contribute to designing, building, evaluating, and refining Spotify’s product by ensuring that our ML/NLP development is always linguistically informed
– Develop NLP components: write rules, build grammars/FSTs, create annotation systems or mappings for the target language
– Collaborate with a cross-functional agile team spanning user research, design, data science, product management, and engineering to build new product features that advance our mission to connect artists and fans in personalized and relevant ways
– Help drive optimization, testing, and tooling to improve quality, with a focus on understanding all people and properly handling ambiguity in language
– Evaluate failure patterns to come up with solutions for expanding linguistic coverage
– Help give hands-on linguistic and language engineering leadership to one of Spotify’s most important business areas, allowing people to drive their audio listening experience with their voices
– Provide insights by using foundational knowledge across phonology, phonetics, syntax, semantics, ontology, program management, human subject research, experimental design, statistics, corpus linguistics, large scale data acquisition, or any combination thereof
– Take on complex language data-related problems using a combination of live and generated data
– Use modelling (ML and NLP) tools to bootstrap and test new functionalities
– Analyze system performance and identify areas for improvement
– Collaborate with Data Curators, Data Engineering, and NLP developers on data collection and development efforts
– Ensure that system design takes into account cross-language variability and is not build on assumptions in any one language
– Develop individually to continue to grow your impact, and help mentor peers
Who you are
– Possess a strong background in applied or theoretical linguistics, computational linguistics, or cognitive science
– PhD + 2 years experience or Masters + 4 years of experience in computational linguistics, language data processing, semantics, and/or syntax
– Have worked with language annotation or other forms of data markup for NLP applications at production scale
– Experienced with data ETL for NLP applications or research analysis
– Conversational or near-native fluency in at least one non-English language
– You care about data-driven development, reliability, and disciplined experimentation
– You love your customers even more than your code
– You have excellent communication, strong organizational skills, and very detailed oriented
– You have experience and passion for mentoring and encouraging collaborative teams.
Preferably, you’ll also:
– Have experience with data analysis processes (R, Matlab, etc…)
– Have experience programming in Perl, Python, or another scripting language
– Have experience working with cloud platforms like GCP or AWS.
– Have experience in writing grammars and building Finite State Transducers (FSTs).
– Have experience with statistical language modelling
– Are comfortable working with speech and text language data in multiple languages
– Are experienced with ontologies, taxonomies, and other semantic meaning representation schemas
– Familiar with version control systems and agile software development practices
We are proud to foster a workplace free from discrimination. We strongly believe that diversity of experience, perspectives, and background will lead to a better environment for our employees and a better product for our users and our creators. This is something we value deeply and we encourage everyone to come be a part of changing the way the world listens to music.