Employer listing
Staff+ Software Engineer, Memory & Search
Anthropic
New York City, Ny · hybrid · full time · Staff
$405,000 - $485,000
About the Role
Anthropic is looking for Software Engineers to join the Memory & Search team. We own how Claude remembers you and how it finds what it needs, across Claude.ai, Cowork and Claude Code. That spans the user-facing experience (what Claude remembers, how people see and edit it, how search surfaces the right conversation) and the shared infrastructure underneath it—the memory service, indexing, retrieval and vector search.
We are looking for product engineers who have shipped user-facing products at scale, have a sharp sense for what makes a product feel good, and have built agentic systems where the model, the tools, and the user interface work together.
Key Responsibilities
- Design, build, and ship memory and search experiences across Claude.ai, Cowork, and Claude Code, owning them end-to-end from backend services through model tools to the user interface.
- Run product experiments on the memory and search stack: form hypotheses, build demos, test with real users, measure, and decide whether to persevere or pivot.
- Shape how Claude uses memory and retrieval inside its agentic loop, including what the model stores, when it searches, how results are ranked and presented, and how users stay in control.
- Define and track metrics to measure memory utility, building evaluations that monitor quality over time.
- Improve search relevance and recall across conversations and memories, working with embeddings, hybrid retrieval, ranking, and presentation interfaces.
- Partner with product, design, privacy, legal, and safeguards to ship features that respect user consent and enterprise requirements (e.g., CMEK, data retention).
- Raise the bar on product quality across the team via design reviews, code reviews, and setting standards for latency, polish, and reliability.
- Share on-call responsibilities for owned systems.
Minimum Qualifications
- Experience building and operating user-facing products used by a large audience, including backend services.
- Experience building agentic systems or LLM-powered products, including tool use, retrieval, and prompt or context design.
- Strong programming skills in Python and TypeScript across backend services and web front ends.
- Proven track record of taking a product or feature from zero to launch, iterating based on usage data and user feedback.
- Experience defining product metrics and running experiments to guide decisions.
- Strong product judgment and communication skills working with cross-functional partners.
- Interest in AI safety and Anthropic's mission.
Preferred Qualifications
- Experience as a founder, early-stage engineer, or taking zero-to-one products to launch.
- Experience building search or retrieval systems (embeddings, vector search, hybrid lexical and semantic retrieval, ranking).
- Experience building evaluations for LLM/ML systems or measuring retrieval and ranking quality.
- Experience with consumer products with strong retention or personalization systems.
- Experience handling sensitive data or enterprise requirements (CMEK, data residency, HIPAA).
- Experience with latency-sensitive, performance-critical product work.
- Experience mentoring engineers or setting technical direction for a team.
Benefits
Anthropic offers competitive compensation and benefits, optional equity donation matching, generous vacation and parental leave, flexible working hours, and vibrant office spaces.