10 hours ago
Base Salary
$350k - $850k/yr
Responsibilities
- Design, build, and run capability evaluations and measurement instruments at scale.
- Build data and analysis pipelines that transform large volumes of model outputs and telemetry into reliable metrics.
- Rapidly prototype, validate, and refine new measurement instruments.
- Review and supervise AI-written code as part of the normal workflow.
- Work with research scientists and partner teams to define meaningful measurements.
- Contribute to internal write-ups and public reporting.
Requirements
- Ship an evaluation, data product, or research library end to end.
- Prototype quickly and be comfortable discarding code when appropriate.
- Handle messy, large-volume data without over-engineering.
- Run experiments on large language models rather than only processing their outputs.
- Work effectively from vague research questions instead of fully specified requirements.
- Communicate results clearly and collaborate closely with researchers.
- Preferred qualifications include building LLM evaluation harnesses or benchmark infrastructure.
- Preferred qualifications include large-scale ML or data infrastructure experience, tools or libraries used by other researchers, and experience identifying errors in AI-written code.
Benefits
- Annual base salary range is $350,000—$850,000 USD.
- Hybrid policy currently expects staff to work from an office at least 25% of the time, with some roles requiring more office time.
- Anthropic offers competitive benefits, optional equity donation matching, generous vacation and parental leave, flexible working hours, and office collaboration space.
Categories
Data EngineeringML Engineering
About Anthropic
Anthropic builds large language models and the Claude AI assistant for developers and enterprises, offered via API access and enterprise plans. Founded in 2021 and headquartered in San Francisco, it distributes Claude through its own platform and via partners such as Amazon Bedrock and Google Cloud’s Vertex AI. Its work emphasizes model reliability, interpretability, and practical tooling for tasks like coding assistance, analysis, and customer support automation.