Prompt Engineer, Agent Prompts & Evals
Anthropic · New York, NY
- On site
- Full-time
- $365,000 / year
- New York, NY
Job highlights
- Build AI-first products, features, and evaluations.
- Bridge AI capabilities with real product experience.
- Become expert on Claude's behaviors and quirks.
- Shape AI infrastructure: system prompts, tool prompts, skills.
- Support concurrent projects across multiple product teams.
About the role
About Anthropic
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.
About The Role
We ’re looking for prompt and context engineers to join our product engineering team to help build AI-first products, features, and evaluations. Your mission will be to bridge the gap between model capabilities and real product experience, working with product teams to build consistent, safe, and beneficial user experiences across all product surfaces.
You will be deeply involved in new product feature and model releases at Anthropic, combining engineering expertise with an understanding of frontier AI applications and model quality. You’ll become an expert on Claude’s behavioral quirks and capabilities and apply that knowledge to deliver the best possible user experience across models and domains. You’ll be the first resource for product teams working on Claude’s AI infrastructure: system prompts, tool prompts, skills, and evaluations.
This role requires someone who can effectively balance caring deeply about making Claude the best it can be while also supporting a wide variety of concurrent projects and efforts across many product teams.
Key Responsibilities
- Prompt Engineering Excellence: Design, test, and optimize system prompts and feature-specific prompts that shape Claude’s behavior across consumer and API products.
- Evaluation Development: Build and maintain comprehensive evaluation suites that ensure model quality and consistency across product launches and updates.
- Cross-functional Collaboration: Partner closely with product teams, research teams, and safeguards to ensure new features meet quality and safety standards.
- Model Launch Support: Play a critical role in model releases, ensuring smooth rollouts and catching regressions before they impact users.
- Infrastructure Contribution: Help build and improve the frameworks and tools that allow teams to develop and test prompts and features with confidence.
- Knowledge Transfer: Mentor product engineers on prompt engineering best practices and help teams build their first evaluations.
- Rapid Iteration: Work in a fast-paced environment where model capabilities advance daily, requiring quick adaptation and creative problem-solving.
Required Qualifications
What We’re Looking For
- 5+ years of software engineering experience with Python or similar languages.
- Demonstrated experience with LLMs and prompt engineering (through work, research, or significant personal projects).
- Strong understanding of evaluation methodologies and metrics for AI systems.
- Excellent written and verbal communication skills – you’ll need to explain complex model behaviors to diverse stakeholders.
- Ability to manage multiple concurrent projects and prioritize effectively.
- Experience with version control, CI/CD, and modern software development practices.
Preferred Qualifications
- Experience with Claude or other frontier AI models in production settings.
- Background in machine learning, NLP, or related fields.
- Experience with A/B testing and experimentation frameworks (e.g., Statsig).
- Familiarity with AI safety and alignment considerations.
- Experience building tools and infrastructure for ML/AI workflows.
- Track record of improving AI system performance through systematic evaluation and iteration.
You Might Thrive in This Role If You…
- Get excited about the nuances of how language models behave and love finding creative ways to improve their outputs.
- Enjoy being at the intersection of research and product, translating cutting-edge capabilities into user value.
- Are comfortable with ambiguity and can define success metrics for novel AI features.
- Have a strong sense of ownership and drive projects from conception to production.
- Are passionate about building AI systems that are helpful, harmless, and honest.
- Thrive in collaborative environments and enjoy teaching others.
Salary and Logistics
The annual compensation range for this role is listed below.
For sales roles, the range provided is the role’s On Target Earnings (
Skills & topics
- Prompt Engineering
- LLM
- AI
- Python
- Software Engineering
- Natural Language Processing
- Machine Learning
- AI Safety
- Evaluation
- Product Engineering
How to get hired
- Tailor your resume: Highlight relevant software engineering and LLM prompt engineering experience.
- Showcase LLM knowledge: Detail projects, research, or coursework demonstrating expertise with large language models.
- Emphasize collaboration: Provide examples of cross-functional work with product and research teams.
- Demonstrate evaluation skills: Quantify experience with AI evaluation methodologies and metrics.
- Prepare for technical interviews: Be ready to discuss Python, LLMs, and software development practices.
Technical preparation
Master Python and related programming skills.,Practice LLM prompting and evaluation techniques.,Familiarize with AI safety and alignment.,Prepare for system design and coding interviews.
Behavioral questions
Describe a complex model behavior you explained.,How do you balance multiple project priorities?,Share an experience translating research to product.,How do you approach ambiguous project goals?
Frequently asked questions
- What are the key responsibilities for a Prompt Engineer at Anthropic?
- As a Prompt Engineer at Anthropic, you will design, test, and optimize prompts for Claude, develop evaluation suites for model quality, collaborate with product and research teams, support model launches, and contribute to prompt development frameworks. You will also mentor other engineers on prompt engineering best practices.
- What qualifications are required for the Prompt Engineer role at Anthropic?
- We require 5+ years of software engineering experience with Python or similar languages, demonstrated experience with LLMs and prompt engineering, a strong understanding of AI evaluation methodologies, excellent communication skills, and the ability to manage multiple projects. Experience with version control and CI/CD is also necessary.
- What are the preferred qualifications for a Prompt Engineer at Anthropic?
- Preferred qualifications include experience with Claude or other frontier AI models in production, a background in machine learning or NLP, experience with A/B testing frameworks, familiarity with AI safety, and experience building ML/AI workflow tools.
- What kind of environment can I expect at Anthropic?
- Anthropic is a public benefit corporation focused on building safe and beneficial AI. The environment is collaborative, with a focus on large-scale research efforts and advancing steerable, trustworthy AI. They value impact and encourage diverse perspectives.
- Does Anthropic offer visa sponsorship for this Prompt Engineer role?
- Yes, Anthropic does sponsor visas for this role. They will make every reasonable effort to assist candidates who receive an offer with obtaining a visa.
- What is the salary range for the Prompt Engineer position?
- The annual compensation range for this Prompt Engineer role at Anthropic is $320,000 to $405,000 USD.
- What is Anthropic's stance on AI usage during the application process?
- Anthropic has a policy regarding AI usage in the application process. Candidates are encouraged to learn about this policy, which is available on their careers page or through direct communication.
- What is the work arrangement for this Prompt Engineer role?
- This is a location-based hybrid role, with staff expected to be in the office at least 25% of the time. Some roles may require more in-office presence.
- How can I ensure my application stands out for the Prompt Engineer position at Anthropic?
- To make your application stand out, clearly articulate your experience with LLMs and prompt engineering, showcase your software engineering background, highlight your collaboration skills, and demonstrate your understanding of AI evaluation. Quantifiable achievements are always a plus.
- What kind of impact can I have as a Prompt Engineer at Anthropic?
- As a Prompt Engineer, you will directly influence user experiences by bridging model capabilities with product features, ensuring AI systems are consistent, safe, and beneficial. You'll play a critical role in shaping the behavior of advanced AI models like Claude.