Data Engineer ADAS Fleet Analytics

Mercedes-Benz uses large-scale vehicle telemetry to evaluate, monitor, and improve its Advanced Driver Assistance Systems. As a Data Engineer on the US ADAS Data & Forensics team, you will build and operate the data pipelines that turn raw vehicle signals into trusted KPIs, fleet dashboards, and campaign-health monitoring for management and the engineers who calibrate ADAS functions. You will own the full data lifecycle, including real-time ingestion, binary protocol decoding, Bronze/Silver/Gold processing with PySpark and Delta Lake, and delivery through APIs and dashboards. You will also manage data campaigns end to end, including VIN enrollment, fleet-health tracking, coverage-gap detection, and the Sold to Consented to Capable to Active vehicle funnel. The architecture is evolving toward applied AI, and you will build the data infrastructure required for vision-language models, LLM-based event classification, embedding retrieval, and model-based event scoring.

Relocation assistance (domestic or international) is not provided for this position.

Job Responsibilities:

• Design and maintain scalable telemetry pipelines using Event Hub, Medallion architecture, Delta Lake MERGE, schema evolution, and blue/green data deployments.
• Own campaign and fleet management, including enrollment rosters, ingestion-completeness monitoring, VIN reconciliation, and automated coverage alerts.
• Develop fleet KPIs for engineering, including safety events and takeover analysis; operations, including data freshness and pipeline health; and management, including trends and cohort comparisons.
• Build ML-ready data infrastructure, including video and signal pipelines for SSR recordings, embedding stores, feature-engineering layers, and model-output integration into Gold.
• Operate the Azure data platform, including ADLS Gen2, Synapse Spark, Event Hub, and Container Apps, and support Terraform-managed infrastructure and CI/CD.
• Write automated tests, maintain documentation alongside code, and participate in code reviews and incident response.

Minimum Qualifications:

• Bachelor's or Master's degree in Computer Science, Data Engineering, or a related field. Equivalent experience may be considered.
• 2-5 years of experience in data engineering or big-data analytics with production pipeline ownership.
• Strong Python, PySpark DataFrame API and performance-tuning skills, and SQL skills including window functions and aggregations.
• Experience with a columnar or transactional data-lake technology such as Delta Lake, Iceberg, Hudi, or managed Parquet.
• Experience with automated testing for data pipelines and Git-based development workflows.
• Ability to diagnose production failures, including schema conflicts, data skew, and memory issues, and communicate trade-offs to technical and non-technical stakeholders.

Preferred Qualifications:

Strongly Preferred

• Medallion or other layered data-processing patterns.

• Cloud data-platform experience in Azure, AWS, or GCP.

• Parquet schema design and schema evolution.

• Production data-quality practices, including deduplication, idempotency, and data contracts.

• Time-series, IoT, or vehicle-telemetry data.

Nice to Have

• DuckDB or PyArrow; FastAPI or analytical API delivery; blue/green data deployments.

• ML data infrastructure, including feature stores, embedding pipelines, vector databases, or video pipelines.

• Fleet or campaign management for vehicle or IoT programs.

• Automotive data privacy, including CCPA; ADAS or connected-vehicle domain knowledge.

• Azure Data Engineer or Databricks certification.

• English required; German is an advantage.