Sr. Python Engineer in ML

About XITE

It’s our mission to share our passion for music videos with the world and invite people to experience music beyond listening: to see your music.

XITE is dedicated to building the best music video experience in the world. Based in Amsterdam, XITE now reaches 100 million households across multiple territories through linear networks, interactive TV apps and on-demand streaming services. The company revolutionised the way audiences experience music videos by allowing viewers to search, like and skip through its entire catalogue, enjoy channels curated by its team of music experts and create their own channel based on a genre, decade, style or mood using its unique Mixer feature. XITE has a full music video catalogue through agreements with all major and top independent music labels and distributors, and works to expand this offering every day.

About the role
We are looking for a passionate Mid+/Senior Python engineer in the Data/ML domain to join us. Together with the rest of the team you will be responsible for our machine learning services in production: software and service design/development, monitoring, practical MLOps, performance and architecture. Our technical stack includes Python, Scala, Kafka, ClickHouse, Docker, Bazel, Kubernetes, GCP, Superset and many other, mostly open source, technologies. To accomplish your goals you will take a core role for a team of data and machine learning engineers, working closely with the Data Science, Data Analytics, and Backend Engineering teams, as well as other technical teams and non-technical stakeholders within XITE.

Responsibilities

• Design, develop and scale new/existing data and machine learning pipelines (ETLs, feature stores, productize model training and serving), data products and services.

• Resolve problems, with end-to-end ownership of machine learning and data preparation/transformation pipelines.

• Assist colleagues across technical challenges.

• Design, test, install and maintain highly scalable and data-intensive systems.

• Review, maintain, refactor and extend distributed systems in production. Support other teams for usage and integration with those systems.

• Maintain the technical excellence of the data, ML and software engineering practices.

• Work on shared libraries, infrastructure and building blocks within monorepo space.

• Work with the Product Manager and other stakeholders, taking part in forming, prioritising and executing data intensive products backlog.

• Broad interest and experience within ML/Data domains.

• Proven professional experience as a Software Engineer, Machine Learning Engineer or Data Engineer, working with systems and data infrastructure at scale.

• Experience with crafting and building large scale data pipelines in distributed environments with technologies such as Kafka, ClickHouse, Elastic, Cassandra, Spark/PySpark or similar.

• Experience with data streams processing tools and concepts.

• Experience optimising ML models, services, pipelines and procedures for performance, cost and usability.

• Knowledge of the main architecture models and concepts like replication, sharding, consistency, horizontal and vertical scaling, idempotency.

• Experience with MLOps practises, building and deploying ML models and data pipelines.

• Preferably a university degree in Software Engineering or other relevant field or comparable work experience.

• Experience with data pipeline orchestrators such as AirFlow, Kubeflow, Dagster or similar.

• Excellent analytical and communication skills.

• Experience in working with monorepo environments (e.g. Bazel based) is a plus.

• Experience in operationalising recommender systems is a plus.

• For this role we want you to be in our office regularly, we are looking for a candidate that is already living in the Netherlands or open to relocation. 

Our Tech Stack

• Python 3 (Pandas, Polars, NumPy, Pydantic), Scala (cats, cats-effect, fs2).

• Kafka, ClickHouse, PostgreSQL, Redis, MongoDB, Memgraph, GCP Buckets, MLFlow, Prometheus.

• Bazel, Docker, Kubernetes, Airflow, GCP.

• GitHub, CircleCI, Ansible, Superset, Grafana and many other, mostly open source, technologies.

Working at XITE

Here at XITE we make sure you’re taken care of by providing you the opportunity to develop your career in a young, fast growing and international company. We provide a challenging work environment where you have a lot of autonomy, flexible working hours and no day will be the same for sure. We don’t hire assholes! All XITE’ers are different and authentic in their own way, but we all have kindness in common. Like professionalism and a flexible and an optimistic attitude. And let’s not forget; We have a passion for music and good food. That’s why we have chef prepared lunches, drinks, rooftop BBQ's! Click here to see all our benefits.

Up for the challenge? Then hit that ‘Apply for this Job’ button!