Data Engineer

Unacast is a global location intelligence and insights company transforming our understanding of human activity in the physical world. Using state-of-the-art machine learning and artificial intelligence, Unacast extracts valuable information from location data, delivering trustworthy, reliable, and privacy-friendly location intelligence. Companies across industries, at every stage of growth, rely on Unacast’s actionable human mobility insights to make more informed decisions that better align with the world around them.

We are hiring for a Data Engineer with interests in ML

This Data Engineering position is for our Visitation team, which is responsible for building an understanding of circumstances at physical locations within our cities. The team builds data products that are used by our SaaS application, APIs and integrated directly with our clients. The Visitation team is a part of our Engineering division and you will report to the team lead. The position is hybrid where you will be expected to work 2-3 days from our office located in the City Center of Pilsen in the Czech Republic.

Responsibilities working as a Data Engineer in the Visitation team

• Designing, creating and operating data products using cloud technologies with an extra focus on solving for operational and computational processing challenges.
• Operate and improve ETL pipelines and feature-stores running at non-trivial scale within a modular environment, in order to align with data-minimisation best practices.
• Manage and develop data production monitoring and testing capabilities to ensure outbound data-feeds and new data versions are of Unacast quality. This includes continuous checking of signal data and input features; groundtruth and real-world invariant testing; as well as model-drift.
• Writing and maintaining a professional code base and production environment together with the team, QA, testing, DevOps, deployment, monitoring and debugging.
• Writing SQL against our data to retrieve information in an efficient manner.
• Analyze data issues or client questions in our data and clearly communicate the challenges.
• Optimizing data flows, storage and architectures to improve robustness, latency, throughput and cost indicators

These are the requirements for the position:

• An academic degree equivalent to a Bachelor's or higher in Computer Science or similar.
• At least 3 years of experience in ML/Data Engineering or Backend Software Engineering.
• Experience building productionized ETL data pipelines that run in a cloud environment.
• Excellent communication skills and proficiency in English.
• Passion and positivity, with determination. Tendencies to persist and adapt when faced with challenges, turning fast failures into fast lessons.

It is also positive if you have experience in:

• Google Cloud and Google Big Query

• Apache Airflow

• MLOps or DevOps

• Python and SQL

• Geospatial, temporal or statistical data

When onboarded we expect you to:

• Demonstrate a proactive and entrepreneurial mindset
• We are a startup, so things change fast. You need to be agile and proactive on this journey
• Our clients are using our products daily, so some on-call will be required