Software Engineer, Memory & Search
Anthropic · New York City, NY; New York City, NY | Seattle, WA; Remote-Friendly, United States; San Francisco, CA | New York City, NY | Seattle, WA
About this role
**Software Engineer, Memory & Search — Anthropic** ## About Anthropic Anthropic’s mission is to create reliable, interpretable, and steerable AI systems—safe and beneficial for users and society. ## About the role Join the **Memory & Search** team. You’ll help Claude remember users and find what it needs across **Claude.ai, Cowork, and Claude Code**—covering both the **user experience** (memory, editing, and search surfacing) and the **shared infrastructure** (memory service, indexing, retrieval, and vector search). The team is evolving memory from a periodically synthesized summary to a **dynamic, editable, on-demand** system, unified across products. Search has grown from a top complaint to a relied-upon capability, and the next phase is making memory a compelling, sticky part of using Claude. You’ll run **short, demo-driven experiments**, decide what to keep based on real usage, and help the team operate like a product team. This is a **trust-sensitive** surface involving privacy, consent, and enterprise controls—working closely with product, design, privacy, legal, and safeguards. ## Key responsibilities - Design, build, and ship memory and search experiences end-to-end (backend services → model tools → UI) across Claude.ai, Cowork, and Claude Code - Run product experiments on the memory/search stack (hypothesis → demo → real users → measure → persevere or pivot) - Shape how Claude uses memory and retrieval in its agentic loop (what gets stored, when to search, ranking/presentation, and user control) - Define and track metrics for whether memory improves usefulness; build evaluations to keep quality high as the system evolves - Improve search relevance and recall across conversations and memories (embeddings, hybrid retrieval/ranking, and result presentation) - Partner with product/design/privacy/legal/safeguards to ship features that respect consent and enterprise requirements (e.g., customer-managed encryption keys, data retention) - Raise product quality via design/code reviews and standards for latency, polish, and reliability; share on-call for owned systems ## Minimum qualifications - Experience building and operating user-facing products used by a large number of people (including backend services) - Experience building agentic systems or LLM-powered products (tool use, retrieval, prompt/context design) - Strong programming skills in **Python** and **TypeScript** (backend services + web front ends) - Track record taking a product/feature from idea to launch and iterating based on usage data and feedback - Experience defining product metrics and running experiments to make decisions - Strong product judgment and ability to explain design choices and their impact on users - Strong written and verbal communication; experience working closely with PMs, designers, and non-engineering partners - Interest in AI safety and Anthropic’s mission ## Preferred qualifications - Experience as a founder, early-stage engineer, or taking a product from zero to one - Experience building search/retrieval systems (embeddings, vector search, hybrid lexical/semantic retrieval, ranking) - Experience building evaluations for LLM/ML systems; measuring retrieval/ranking quality - Experience with consumer products with strong retention or personalization systems - Experience shipping features for sensitive data or enterprise requirements (e.g., customer-managed encryption keys, data residency, HIPAA) - Experience with latency-sensitive, performan
Listing freshness
CronJobs last confirmed this listing 1h ago. If its source stops confirming the opening for seven days, this page is removed from active inventory.