Autonomous Plant Data Engineer for Industrial ML

Mariana Minerals; San Francisco (CA); On-site; USD 140,000 - 180,000; Full time

Job summary

Mariana Minerals, a software-first minerals company, seeks a Senior Data Engineer to own end-to-end data domains for autonomous plant operations in San Francisco. You will design pipelines, schemas, and data contracts to make plant data trustworthy for models and decisions.

Work with the PlantOS platform to handle noisy, non-stationary data, build scalable data architectures, and enable production ML with strong quality, observability, and lineage across the enterprise.

Qualifications

• 4+ years in data engineering or a closely related role.
• Strong Python and SQL; design of time-series and analytical data schemas.
• Experience building reliable, orchestrated data pipelines and operating them in the cloud with containers and CI/CD.
• Experience with data quality, observability, and lineage in messy real-world sources.
• Self-starter comfortable in high-ambiguity environments, collaborating with process engineers, ML engineers, and operations teams.
• Bonus: experience feeding data to ML systems or working with industrial sensor/historian data.

Responsibilities

• Design and evolve pipelines pulling data from sensors, lab systems, historians, and imagery into databases and warehouses.
• Model time-series and analytical plant data for human analysis and ML training, validation, and monitoring; own data quality and lineage.
• Own the data contracts and interfaces that downstream teams rely on; collaborate with ML engineers on model training pipelines.
• Build the data architecture feeding production ML and monitoring layers with ML engineers.
• Mentor earlier-career engineers and define data contracts across teams.
• Balance boundary work with ML: you own the platform interface while ML engineers own features and models.

Skills

Python

SQL

Time-series

Data pipelines

Cloud

CI/CD

Observability

Data quality

Self-starter

Tools

CI/CD tooling

Job description

Mariana Minerals, a software-first minerals company, seeks a Senior Data Engineer to own end-to-end data domains for autonomous plant operations in San Francisco. You will design pipelines, schemas, and data contracts to make plant data trustworthy for models and decisions.

Work with the PlantOS platform to handle noisy, non-stationary data, build scalable data architectures, and enable production ML with strong quality, observability, and lineage across the enterprise.