Research Engineer Model Evaluations
AI safety and research company building reliable, interpretable, and steerable AI systems, including the Claude product family and developer platform.
Maintainer signals as of 9/24/2026
Funding history
About Anthropic
Anthropic PBC develops frontier AI systems and deploys them through Claude products and the Claude Platform, with a stated focus on safety, interpretability, and steerability.
Skills
Candidate Availability
Required and preferred rules are kept separate and reflect the wording in the original posting.
About the Role
You will design and implement evaluations for Claude’s capabilities, build reliable distributed evaluation infrastructure, and create dashboards that communicate model health. You will investigate anomalous results during training, improve evaluation tooling, run benchmarking experiments, and work with researchers to define and interpret measurable outcomes.
Requirements
- Python
- Distributed systems
- Data pipeline
- Technical communication
- Production support
- AI safety
Responsibilities
- Design and run evaluations of Claude's capabilities and safety properties
- Build and harden a distributed evaluation execution platform
- Own dashboards for monitoring model health during training
- Debug anomalous evaluation results during training runs
- Improve evaluation tooling, libraries, and workflows
- Partner with research teams to define measurements and interpret results
- Run experiments on prompting, sampling, and scaffolding choices
- Communicate evaluation results to internal and external stakeholders
Benefits
- Optional equity donation matching
- Generous vacation
- Parental leave
- Flexible working hours