Description
Job Overview
As a Research Engineer on Takeoff Intel at Anthropic, you will build and run evaluation and measurement instruments for AI R&D capabilities. This role involves working across various aspects such as evals infrastructure, large-scale data processing, and analysis tooling, with a focus on shipping impactful projects.
Responsibilities
- Design, build, and run capability evaluations and measurement instruments at scale.
- Develop data and analysis pipelines to turn model outputs and telemetry into reliable metrics.
- Prototype new instruments quickly, validate them, and decide what to keep.
- Review and supervise AI-written code as part of the workflow.
- Collaborate with research scientists to define what's worth measuring.
- Contribute to internal write-ups and public reporting.
Requirements
- Experience shipping an evaluation, data product, or research library end-to-end.
- Ability to prototype quickly and handle messy, large-volume data.
- Experience running experiments on large language models.
- Comfortable working from vague questions rather than specs.
- Clear communication and collaboration skills.
Nice to Have
- Built evaluation harnesses or benchmark infrastructure for LLMs.
- Experience with large-scale ML or data infrastructure.
- Developed tools or libraries relied on by other researchers.
- Track record of catching errors in AI-written code.
Compensation
The annual compensation range for this role is $350,000-$850,000 USD.
Logistics
- Remote-friendly with travel required.
- Minimum education: Bachelor’s degree or equivalent.
- Required field of study: Relevant to the role.
- Minimum years of experience: Correlates with internal job level requirements.
This listing is enriched and indexed by YubHub. To apply, use the employer's original posting:
https://job-boards.greenhouse.io/anthropic/jobs/5416882008