Anthropic
Staff+ Software Engineer, Memory & Search
$405K–$485K
New York City, NY +7 · Remote · Staff · Full-time · Posted Oct 19, 2026
- Location
- New York City, NY
New York City, NY
Seattle, WA
Remote-Friendly, United States
San Francisco, CA
New York City, NY
Seattle, WA
San Francisco, California, United States - Experience
- Years required correlate with internal job-level requirements; no specific number stated.
- Education
- Bachelor’s degree or an equivalent combination of education, training, and/or experience; relevant field of study demonstrated through coursework, training, or professional experience.
- Visa sponsorship
- Visa sponsorship is available, but not for every role or candidate; Anthropic says it will make every reasonable effort to obtain a visa for candidates it offers and provides immigration-lawyer support.
About the job
Build and improve end-to-end memory and search experiences across Claude products, using product experiments and user feedback to make AI more useful while respecting privacy and enterprise controls.
What you'll do
- Design, ship, and operate memory and search features across Claude.ai, Cowork, and Claude Code, spanning backend services, model tools, and user interfaces.
- Run user-facing experiments, define metrics and evaluations, and improve retrieval relevance, recall, and ranking.
- Partner with product, design, privacy, legal, and safeguards teams to deliver reliable features that respect consent and enterprise requirements.
What they ask for
- Experience building and operating user-facing products at scale, including backend services.
- Experience building agentic systems or LLM-powered products, including tool use, retrieval, and prompt or context design.
- Strong Python and TypeScript programming skills across backend services and web front ends.
- Track record of taking products or features from idea to launch, using metrics, experiments, and user feedback to iterate.
Nice to have
- Founder, early-stage engineer, or experience taking a product from zero to one.
- Experience with search or retrieval systems, LLM/ML evaluations, personalization, sensitive data, performance-critical work, or technical mentorship.
Pay
$405,000 — $485,000 USD annual salary (base salary)
Tools
Python, TypeScript, embeddings, vector search, hybrid retrieval, ranking
AI focus
Build agentic memory and retrieval systems and LLM-powered product experiences, including tool use, model context, and quality evaluations.
Model-written summary · the original posting is authoritative