Scientific AI Data & Evaluation Scientist

Periodic Labs; Menlo Park (CA); On-site; USD 250,000 - 350,000; Full time

Benefits offered by this job

Visa sponsorship

Job summary

Periodic Labs is hiring for a role focused on evaluations and data to accelerate scientific AI development in materials, energy, and beyond. You will coordinate with computational and experimental scientists to translate complex workflows into robust evaluations and RL benchmarks.

You will build datasets, environments, and pipelines, ensuring a tight feedback loop between scientific use cases, model evaluation, and training data. Visa sponsorship is available.

Qualifications

• Bachelor's degree or equivalent experience.
• Experience translating scientific workflows into evaluations and RL environments.
• Strong software and data engineering skills at scale.
• Experience sourcing and curating external datasets.

Responsibilities

• Own the evaluation and data strategy across the training stack, identifying capability gaps and shaping the roadmap with leads of physical science and AI research.
• Translate advanced scientific workflows into rigorous evals, benchmarks, and RL environments with domain experts.
• Source, evaluate, and procure external datasets across chemistry, physics, materials science, mathematics, simulations, and instrumentation.
• Build robust pipelines to ingest, clean, and transform large-scale datasets from heterogeneous sources.
• Build tooling and analysis workflows to help researchers inspect data and understand model failures.

Skills

Evaluation design

Data pipelines

Data quality judgment

Software engineering

Research mindset

Education

Bachelor's degree

Job description

Periodic Labs is hiring for a role focused on evaluations and data to accelerate scientific AI development in materials, energy, and beyond. You will coordinate with computational and experimental scientists to translate complex workflows into robust evaluations and RL benchmarks.

You will build datasets, environments, and pipelines, ensuring a tight feedback loop between scientific use cases, model evaluation, and training data. Visa sponsorship is available.