Staff Engineer, ML Evaluation & Metrics Platform

Causal Labs; San Francisco (CA); On-site; USD 180,000 - 240,000; Full time

Job summary

Causal Labs in San Francisco is building a central evaluation framework for a Large Physics foundation Model, enabling measurable, comparable progress across teams.

You will design pipelines, benchmarks, and visualizations, and establish statistical methodologies to separate true improvements from noise, collaborating with research and domain teams.

The role emphasizes end-to-end ownership and rapid execution in a hands-on engineering culture.

Qualifications

• Proven experience building data or evaluation pipelines at scale.
• Ability translate research outputs into metrics and visualizations that teams rely on.
• Strong grasp of probability and statistics.
• Experience building backend and frontend tooling.
• End-to-end ownership of deliverables.

Responsibilities

• Design a central evaluation framework used by all teams.
• Implement evaluation pipelines, benchmarks, and baselines.
• Create visualization and dashboard tools for interpreting results.
• Establish sound statistical methods to distinguish improvements from noise.
• Collaborate with research and domain teams to define domain-specific metrics.

Skills

Software engineering

Data/evaluation pipelines

Metrics/benchmarks/visualizations

Statistics & uncertainty

Full-stack development

Job description

Causal Labs in San Francisco is building a central evaluation framework for a Large Physics foundation Model, enabling measurable, comparable progress across teams.

You will design pipelines, benchmarks, and visualizations, and establish statistical methodologies to separate true improvements from noise, collaborating with research and domain teams.

The role emphasizes end-to-end ownership and rapid execution in a hands-on engineering culture.