Machine Learning Engineer

Tech Level: Senior
English Level: Upper-Intermediate
Employment Type: Full-time
Time Zone: CET
Start Date: ASAP
Duration: 12+ months

About the Project

The team is responsible for building and improving address search and geocoding solutions that enable users to find accurate and relevant locations with ease. The focus areas include query understanding, geocoding, hybrid search, and enhancing prediction accuracy for pickup and drop-off locations through advanced ML models.

Project Phase: Ongoing

Key Responsibilities

• Design ML systems end-to-end, including data analysis, annotation, and processing across multiple research areas or multimodal scenarios.
• Lead data preparation and computation across all development stages.
• Translate business goals and metrics into engineering and data science tasks.
• Own the entire data science product lifecycle — from pipeline development and implementation to A/B testing and production rollout.
• Create innovative ML-driven services to improve map accuracy and coverage.
• Work on search relevance optimization, personalization, and multilingual support within the Geo domain.
• Enhance route precision and ETA accuracy.
• Contribute to Geo data management — including ingestion pipelines, anomaly detection, and data reliability improvement.
• Perform geospatial analysis and extract actionable insights from location data.

Requirements

• Bachelor’s degree in Statistics, Mathematics, Computer Science, Machine Learning, or a related field.
• 5+ years of hands-on experience as an ML Engineer, Applied Scientist, or Data Scientist.
• Strong background in Python and frameworks for streaming, batch, and asynchronous data processing.
• Proficiency with MLOps tools and lifecycle management of ML models.
• Experience designing and maintaining ML-powered services in production environments.
• Familiarity with Geo / Maps ML applications.
• Expertise in multiple ML domains (e.g., Computer Vision, NLP).
• Deep understanding of classical ML, deep learning, and underlying mathematical concepts.
• Solid experience in ML system design and MLOps practices for production.
• Strong grasp of software system design principles.
• Experience in experimental design and hypothesis validation.
• Awareness of security, risk, and control practices in production systems.
• (Plus) Knowledge of Golang, event-driven systems, or distributed deployment environments.

Tech Stack

Python, Go (nice to have), SQL, Kafka / Spark / Flink, PostGIS, ElasticSearch
 

Interview Process

1. English proficiency check
2. Internal technical interview
3. Final technical interview with the project team