Anthropic’s mission is to create reliable, interpretable, and steerable AI systems. We want AI to be safe and beneficial for our users and for society as a whole. Our team is a quickly growing group of committed researchers, engineers, policy experts, and business leaders working together to build beneficial AI systems.
As a Prompt Engineer on the Claude Code team, you'll own Claude's behaviors specifically within Claude Code — ensuring users get a consistent, safe, and high-quality experience as we ship new models and evolve the product. This is a highly specialized role sitting at the intersection of model behavior and product quality.
You'll be the expert on how Claude behaves inside Claude Code, owning and maintaining the system prompts that ship with each new model snapshot. When a new model drops, you're the person making sure Claude Code feels right within days — not weeks. You'll work closely with Model Quality and Research to understand emergent behaviors and behavioral regressions, and with product and safeguards teams to respond quickly when something goes wrong.
This role requires someone who can move fast on behavioral tuning while maintaining rigor, and who cares deeply about the end-to-end developer experience Claude Code delivers. You'll need strong prompting skills, excellent judgment about model behaviors, and the collaborative skills to work across product, safeguards, and research teams.
Salary: $320,000-405,000 (SWE-G 5-6)
ResponsibilitiesOwn 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
Are a power user of agentic coding tools and have strong intuition about model capabilities and limitations
Thrive in high-intensity environments with fast iteration cycles
Take full ownership of problems and drive them to completion independently
Are skilled at creating and maintaining behavioral evaluations
Have strong technical understanding, including comprehension of agent scaffold architectures and model training processes
Are an experienced coder comfortable working in Python and Typescript
Have independently driven changes through production systems with strong execution and responsiveness
Have experience translating user feedback and product needs into coherent prompts and behavioral specifications
Excel at working across organizational boundaries, collaborating effectively with teams that have differing goals and perspectives
Have experience translating user feedback and behavioral observations into coherent prompt changes and specifications
Care deeply about AI safety and making Claude a healthy alternative in the AI landscape
The annual compensation range for this role is listed below.
For sales roles, the range provided is the role’s On Target Earnings ("OTE") range, meaning that the range includes both the sales commissions/sales bonuses target and annual base salary for the role.
Education requirements: We require at least a Bachelor's degree in a related field or equivalent experience.
Location-based hybrid policy: Currently, we expect all staff to be in one of our offices at least 25% of the time. However, some roles may require more time in our offices.
Visa sponsorship: We do sponsor visas! However, we aren't able to successfully sponsor visas for every role and every candidate. But if we make you an offer, we will make every reasonable effort to get you a visa, and we retain an immigration lawyer to help with this.
We encourage you to apply even if you do not believe you meet every single qualification. Not all strong candidates will meet every single qualification as listed. Research shows that people who identify as being from underrepresented groups are more prone to experiencing imposter syndrome and doubting the strength of their candidacy, so we urge you not to exclude yourself prematurely and to submit an application if you're interested in this work. We think AI systems like the ones we're building have enormous social and ethical implications. We think this makes representation even more important, and we strive to include a range of diverse perspectives on our team.
Your safety matters to us. To protect yourself from potential scams, remember that Anthropic recruiters only contact you from @anthropic.com email addresses. In some cases, we may partner with vetted recruiting agencies who will identify themselves as working on behalf of Anthropic. Be cautious of emails from other domains. Legitimate Anthropic recruiters will never ask for money, fees, or banking information before your first day. If you're ever unsure about a communication, don't click any links—visit anthropic.com/careers directly for confirmed position openings.
We believe that the highest-impact AI research will be big science. At Anthropic we work as a single cohesive team on just a few large-scale research efforts. And we value impact — advancing our long-term goals of steerable, trustworthy AI — rather than work on smaller and more specific puzzles. We view AI research as an empirical science, which has as much in common with physics and biology as with traditional efforts in computer science. We're an extremely collaborative group, and we host frequent research discussions to ensure that we are pursuing the highest-impact work at any given time. As such, we greatly value communication skills.
The easiest way to understand our research directions is to read our recent research. This research continues many of the directions our team worked on prior to Anthropic, including: GPT-3, Circuit-Based Interpretability, Multimodal Neurons, Scaling Laws, AI & Compute, Concrete Problems in AI Safety, and Learning from Human Preferences.
Come work with us!Anthropic is a public benefit corporation headquartered in San Francisco. We offer competitive compensation and benefits, optional equity donation matching, generous vacation and parental leave, flexible working hours, and a lovely office space in which to collaborate with colleagues. Guidance on Candidates' AI Usage: Learn about our policy for using AI in our application process
Top Skills
What We Do
Anthropic is an AI safety and research company that’s working to build reliable, interpretable, and steerable AI systems. Our research interests span multiple areas including natural language, human feedback, scaling laws, reinforcement learning, code generation, and interpretability.
