About the Role
Anthropic's mission is centered on creating reliable, interpretable, and steerable AI systems that are safe and beneficial for users and society. As a Prompt Engineer on the Claude Code team, you will take ownership of Claude's behaviors specifically within the Claude Code product environment. This critical role ensures that users consistently experience a safe and high-quality interaction as new models are deployed and the product evolves. You will become the authoritative expert on Claude's behavior within Claude Code, responsible for maintaining and optimizing the system prompts that accompany each new model snapshot. Your immediate focus will be to ensure that Claude Code functions seamlessly and effectively within days of a new model release. The role demands close collaboration with the Model Quality and Research teams to identify and understand emergent behaviors and regressions, as well as with product and safeguards teams to address any issues promptly. This position requires a fast-paced approach to behavioral tuning while upholding rigorous standards, coupled with a deep commitment to the end-to-end developer experience delivered by Claude Code. Strong prompting skills, excellent judgment regarding model behaviors, and collaborative abilities across diverse technical and product teams are essential.
Responsibilities
- Own Claude Code's system prompts for each new model snapshot, ensuring behaviors feel consistent and well-tuned
- Review production prompt changes and serve as a resource for particularly challenging prompting problems involving alignment and reputational risks
- Lead incident response for behavioral and policy concerns, coordinating with product and safeguards teams
- Scale prompting and evaluation best practices across claude code and product teams
- Deliver product evaluations focused on model behaviors
- Define and streamline processes for rolling out prompt changes, including launch criteria and review practices
- Create model-specific prompt guides that document quirks and optimal prompting strategies for each release
- Collaborate with product teams to translate feature requirements into effective prompts
Requirements
- Power user of agentic coding tools with strong intuition about model capabilities and limitations
- Thrives in high-intensity environments with fast iteration cycles
- Takes full ownership of problems and drives them to completion independently
- Skilled at creating and maintaining behavioral evaluations
- Strong technical understanding, including comprehension of agent scaffold architectures and model training processes
- Experienced coder comfortable working in Python and Typescript
- Independently driven changes through production systems with strong execution and responsiveness
- Experience translating user feedback and product needs into coherent prompts and behavioral specifications
- Excels at working across organizational boundaries, collaborating effectively with teams that have differing goals and perspectives
- Experience translating user feedback and behavioral observations into coherent prompt changes and specifications
- Cares deeply about AI safety and making Claude a healthy alternative in the AI landscape
- Bachelor's degree in a related field or equivalent experience
Qualifications
Not explicitly listed as a separate section.
Benefits
- Competitive compensation and benefits
- Optional equity donation matching
- Generous vacation and parental leave
- Flexible working hours
- Lovely office space in which to collaborate with colleagues
- Visa sponsorship available
- Hybrid policy: in office at least 25% of the time