Senior Data Engineer – Real-Time ML Pipelines

Events by L; Stockholms kommun; On-site; SEK 900,000 - 1,300,000; Full time

Benefits offered by this job

Private health insurance

Pension

Wellness contributions

Office culture and Lab Days

Job summary

Truecaller is seeking a Senior Data Engineer to own the data foundation behind their recommendation and advertising ML systems. You will build feature pipelines, streaming ingestion, and a real-time feature store to power large-scale models and real-time inference.

The role partners with data scientists to bring models from notebook to production, ensuring data contracts, freshness SLAs, and lineage. You will implement scalable pipelines and best practices across the team.

Qualifications

• Strong programming in Python and Spark, with ETL/ELT pipelines.
• Experience with orchestration tool like Airflow in production.
• Experience with large datasets on cloud (GCP preferred; AWS/Azure also fine).

Responsibilities

• Build and own the feature and training-data pipelines for retrieval, ranking, and contextual-bandit models.
• Design streaming pipelines to capture impressions, clicks, conversions in near real time.
• Maintain a real-time feature store for consistent offline/online data.
• Own the ad-event and attribution data backbone for delivery, billing, and partners.
• Collaborate with data scientists to move models from notebook to production, managing data contracts and lineage.
• Create reusable, config-driven frameworks to onboard new models and campaigns.
• Ensure platform reliability at scale with monitoring and data quality checks.

Skills

Python

Spark

ETL/ELT pipelines

CI/CD

Communication

Problem solving

Data science collaboration

Tools

Airflow

Git

Jenkins

BigQuery

Cloud platforms (GCP/AWS/Azure)

Job description

Truecaller is seeking a Senior Data Engineer to own the data foundation behind their recommendation and advertising ML systems. You will build feature pipelines, streaming ingestion, and a real-time feature store to power large-scale models and real-time inference.

The role partners with data scientists to bring models from notebook to production, ensuring data contracts, freshness SLAs, and lineage. You will implement scalable pipelines and best practices across the team.