Cloud Platform - Data Engineer

Lab37; Pittsburgh (Allegheny County); On-site; USD 120,000 - 180,000; Full time

Job summary

Lab37 Robotics in Pittsburgh seeks a Data/ML Platform Engineer to own the data and ML platform powering its robotics fleet. You will build ETL pipelines that transform robot telemetry into actionable analytics, and manage the ML training infrastructure for computer vision models running on robots.

You will work with a small, high-impact platform team to deliver data systems used by product teams, kitchen operations, and engineers deploying ML models to field robots.

Qualifications

• 2+ years of experience in data/platform engineering for robotics or manufacturing contexts.
• Proficient in building ETL pipelines, data warehousing, and model deployment.
• Collaborates closely with data scientists and product teams.

Responsibilities

• Build and maintain ETL pipelines ingesting robot telemetry into BigQuery.
• Manage ML training infrastructure with Argo Workflows on Kubernetes.
• Design data quality checks and observability dashboards for pipeline health.
• Own the data warehouse layer — schema design, incremental loading, and dbt transforms.
• Build dashboard infrastructure (Superset, Grafana) for real-time insights.
• Collaborate with data scientists to productionize model training pipelines.
• Contribute to infrastructure-as-code (Terraform) and CI/CD pipelines for data/ML workloads.
• Participate in on-call rotations for data pipeline reliability.

Skills

Data platform

ETL pipelines

ML training infra

Kubernetes

Argo Workflows

BigQuery

dbt transforms

Observability

Terraform

CI/CD

Superset

Grafana

Tools

BigQuery

Athena

dbt

Kubernetes

Argo Workflows

Terraform

Superset

Grafana

Job description

Lab37 Robotics , is a technology company focused on the development and deployment of robots designed specifically for direct-to-customer food production. Our mission is to revolutionize the food industry by creating innovative robotic solutions that enhance efficiency, quality, and customer satisfaction. We are passionate about pushing the boundaries of technology to deliver cutting-edge products that meet the evolving needs of our clients.

What you’ll do

Take on ownership of the data and ML platform layer that powers Lab37’s robotics fleet. This spans building ETL pipelines that turn raw robot telemetry into actionable analytics, managing the ML training infrastructure that produces the computer vision models running on our robots, and ensuring the observability and reliability of the entire data stack.

Work with a small, high-impact platform team to build the systems that every product team at Lab37 consumes — from data scientists training models, to kitchen operations teams viewing dashboards, to engineers deploying new ML models to robots in the field.

Responsibilities

• Build and maintain ETL pipelines that ingest, validate, transform, and load robot telemetry data into BigQuery for analytics and ML training
• Manage ML training infrastructure using Argo Workflows on Kubernetes — from data extraction through model training, evaluation, and registration
• Design and maintain data quality checks and observability dashboards (the "glass panel" for data pipeline health)
• Own the data warehouse layer — schema design, incremental loading, dbt transforms, and BigQuery/Athena query optimization
• Build dashboard infrastructure (Superset, Grafana) that kitchen operations and leadership teams rely on for real-time insights
• Collaborate with data scientists to productionize model training pipelines — from notebook experiments to reproducible, automated workflows
• Contribute to infrastructure-as-code (Terraform) and CI/CD pipelines for data and ML workloads
• Participate in on-call rotations for data pipeline reliability

What we’re looking for

• 2+