AI Data Engineer

Overview

Quarter hill is seeking a Senior AI Data Engineer to join our forward-thinking team building the next generation of Intelligent Transportation Systems. In this role, you will architect and own the data platform that fuses our computer vision outputs with roadside sensor and lane-controller telemetry, turning raw, high-volume capture data into a reliable foundation for model training, accuracy auditing, and predictive analytics.

You will design the systems that ingest data from roadside equipment at scale, join it into unified transaction records, and expose it for machine learning, reporting, and forecasting.

As part of our data team, you will collaborate closely with machine learning, engineering, and product teams to deliver high-impact data capabilities for our growing SaaS platform. The ideal candidate brings deep experience building production-grade data infrastructure on cloud platforms, a strong grasp of data modeling and quality at scale, and the judgment to translate business questions into robust, maintainable data systems.

• Architect and build pipelines that ingest and fuse images, plate-recognition results, and roadside telemetry into a unified transaction record.

• Own the data-quality, auditing, and metrics layer, defining and computing read rate, per-stage accuracy, character error rate, confidence calibration, and drift as trustworthy, auditable measures.

• Build the infrastructure that feeds predictive analytics such as volume forecasting, revenue and leakage estimation, and equipment-fault prediction.

• Stand up andmaintainannotation andsynthetic-data pipelines (CVAT,Roboflow, Label Studio) that produce training and ground-truth datasets.

• Integrate Service Now incident, asset, and CMDB data to enrich transaction records and feed operational analytics.

• ApplyMLOpsand Data Opsbest  practices for orchestration, testing, deployment, monitoring, and lineage, with clean, modular code.

• Collaborate cross-functionally to translate analytics and product needs into concrete data systems and measurable impact.

This list of responsibilities might not cover everything you'll end up doing.

Required Skills & Experience

• 3+ years in data engineering, witha track recordof shipping production-grade data platforms at scale.

• Master's degree preferred (Bachelor'swith equivalent experience accepted) in Computer Science, Data Engineering, or a related field.

• Deepexpertisebuilding batch and streaming pipelines (Kafka, Airflow,dbt), with strong data modeling and advanced SQL.

• Experience with cloud data platforms (AWS, GCP, or Azure) and infrastructure tooling including Docker and Kubernetes.

• Hands-on Service Now integration into cloud warehouses and lakes (Big Query, Databricks, or Redshift) via Integration Hub and REST APIs, including delta syncs and CDC.

• Applied analytics, including supervised and unsupervised ML, time-series forecasting, and anomaly detection on operational and sensor data.

• Data annotation best practices with CVAT,Roboflow, and Label Studio, including model-assisted labeling and COCO/YOLO formats.

• Nice to have experience generating high-quality synthetic data, including prompt crafting for generative models to produce diverse, label-accurate training data.

• Strong communicator who translates complex data and business needs into actionable decisions for engineering, ML, and product teams.