405K–485K USD / year
Staff+ Software Engineer, Memory & Search
AIHybrid — New York City, NY, Seattle, WA, San Francisco, CA, United States
Published on 2026-10-19
These details were extracted automatically from the original listing. They may not be complete or fully up to date — it's worth checking the original job post.
About this role
Build and ship user-facing memory and search experiences for Claude across Claude.ai, Cowork, and Claude Code. The role spans backend services, agentic model interactions, retrieval, and user interfaces, with a focus on product experiments, quality, and user control.
About the company
Anthropic builds reliable and interpretable AI systems, including the Claude family of models, for businesses and developers. The company focuses on AI safety research and practical AI assistants for enterprise and consumer use.
The team
Memory & Search team
Stack
PythonTypeScriptLLMsEmbeddingsVector searchHybrid retrieval
What you'll do
- Build memory and search features end to end, from backend services through model tools to user interfaces
- Run user-facing product experiments and make decisions based on usage
- Shape how Claude stores memories, searches, ranks results, and presents them to users
- Define product metrics and evaluations for memory and retrieval quality
- Improve search relevance and recall across conversations and memories
- Partner with product, design, privacy, legal, and safeguards on consent and enterprise requirements
- Set quality standards through design and code reviews, and share on-call duties
What we're looking for
- Experience building and operating large-scale user-facing products and their backend services
- Experience building agentic systems or LLM-powered products, including tool use, retrieval, and prompt or context design
- Strong Python and TypeScript skills across backend services and web front ends
- Track record of taking products or features from idea to launch and iterating based on data and feedback
- Experience defining product metrics and running experiments
- Strong product judgment and communication skills, including cross-functional collaboration
- Interest in AI safety and Anthropic’s mission
Nice to have
- Founder, early-stage engineer, or experience taking a product from zero to one
- Experience with search or retrieval systems, embeddings, vector search, hybrid retrieval, or ranking
- Experience building LLM or ML evaluations or measuring retrieval and ranking quality
- Consumer product, retention, or personalization experience
- Experience handling sensitive data or enterprise requirements such as customer-managed encryption keys, data residency, or HIPAA
- Latency-sensitive or performance-critical product experience
- Experience mentoring engineers or setting technical direction
Benefits
- Flexible working hours
- Generous vacation and parental leave
- Optional equity donation matching
- Office collaboration space