Senior Data Engineer - Recommendations
Truecaller3 months ago
Stockholm, SwedenSenior
Responsibilities
- Build and own feature and training-data pipelines for retrieval, ranking, and contextual-bandit models.
- Design near-real-time streaming pipelines that capture impressions, clicks, and conversions for model retraining.
- Stand up and maintain a real-time feature store for consistent offline training and low-latency online inference.
- Own clean, reconciled ad-event and attribution pipelines supporting delivery, billing, and third-party partners.
- Partner with data scientists and ML engineers to productionize models and manage data contracts, freshness SLAs, and lineage.
- Build reusable, config-driven frameworks for onboarding new models and campaigns.
- Maintain platform reliability for billions of daily events through monitoring, data-quality checks, and dependable backfills.
- Set team best practices for pipeline design, testing, and data modeling.
Requirements
- Strong programming skills in Python and Spark and experience building complex, large-scale ETL/ELT pipelines.
- Hands-on experience with an orchestration tool such as Airflow in production ML or analytics workloads.
- Experience working with large datasets on a major cloud provider, with GCP preferred and AWS or Azure also accepted.
- Strong software engineering fundamentals, including testing, CI/CD with Git and Jenkins or similar tools.
- Understanding of production ML data needs, including features, freshness, consistency, and lineage.
- Experience with streaming systems such as Kafka, Flink, or Spark Structured Streaming is preferred.
- Experience with feature stores such as Feast, Vertex AI, Tecton, or an in-house system is preferred.
- Exposure to recommendation, ranking, or advertising ML systems and their supporting data is preferred.
- Knowledge of Kubernetes is preferred.
- Experience managing a data warehouse in BigQuery or Redshift is preferred.
- Strong problem-solving, communication, ownership, and self-motivation skills.
Benefits
- Competitive salary, 30 days of paid vacation, private health insurance, parental leave top-up, pension, and wellness contributions.
- Learning resources, leadership programs, mentoring, hands-on work, internal mobility, and a transparent progression path.
- Choice of preferred computer and phone within the company budget.
- Office-first work culture with some flexibility and on-site meals, snacks, quiet spaces, and team activities.
- Lab Days five times per year for three days each to explore and prototype new ideas.
- Applications must be submitted in English; a background check is part of the recruitment process.
Tech Stack
Amazon RedshiftApache AirflowApache FlinkApache KafkaApache SparkAWSAzureGitGoogle BigQueryGoogle Cloud PlatformJenkinsKubernetesPython
Categories
Data Engineering
About Truecaller
Truecaller builds a mobile app and platform for caller ID, spam and fraud blocking, and contact verification used by consumers and businesses, especially in India and other emerging markets. It monetizes via ads, premium subscriptions, and enterprise solutions like verified business caller ID and messaging. Founded in 2009 and headquartered in Stockholm, the company is publicly listed on Nasdaq Stockholm and reports hundreds of millions of monthly active users.