SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Salary: USD 320,000 - 485,000 / annual
Anthropic is hiring Software Engineers for the Memory & Search team, which owns how Claude remembers users and retrieves information across Claude.ai, Cowork, and Claude Code. The role spans both user-facing experiences (what Claude remembers, how users see and edit memories, how search surfaces relevant conversations) and the underlying infrastructure (memory service, indexing, retrieval, vector search).
Memory recently transitioned from periodically synthesized summaries to a dynamic, editable, on-demand system that now unifies across products. Search has evolved from a top user complaint to a relied-upon feature for finding past work. The team is now focused on discovering product form factors that make memory the most compelling and sticky part of using Claude.
You will be a product engineer who ships user-facing products at scale, has strong product intuition, and has built agentic systems where the model, tools, and UI work together. Key responsibilities include: designing, building, and shipping memory and search experiences end-to-end from backend service through model tools to UI; running product experiments (hypothesis → demo → real users → measurement → decision); shaping how Claude uses memory and retrieval in its agentic loop; defining and tracking metrics for memory usefulness; improving search relevance and recall; partnering with product, design, privacy, legal, and safeguards teams on features respecting user consent and enterprise requirements; and raising product quality standards through design and code reviews.
This is a trust-sensitive surface involving privacy, consent, and enterprise controls. You will work closely with cross-functional partners and treat compliance constraints as part of good product design.
Minimum qualifications:
- Experience building and operating user-facing products used by large numbers 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, with experience across backend services and web frontends
- Track record of taking a product or feature from idea to launch and iterating based on usage data and user feedback
- Experience defining product metrics and running experiments to make decisions
- Strong product judgment: noticing when something feels off and fixing it; explaining why design choices matter to users
- Strong written and verbal communication, with experience working closely with product managers, 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 or retrieval systems (embeddings, vector search, hybrid lexical/semantic retrieval, ranking)
- Experience building evaluations for LLM or ML systems, or measuring retrieval and ranking quality
- Experience on consumer products with strong retention or personalization systems
- Experience shipping features handling sensitive data or meeting enterprise requirements (customer-managed encryption, data residency, HIPAA)
- Experience with latency-sensitive, performance-critical product work
- Experience mentoring engineers or setting technical direction for a team
