Software Engineer, Memory & Search

Location: Remote-friendly, United States, with at least 25% of working time in an Anthropic office; offices listed in New York City, Seattle, and San Francisco.

Annual salary: $320,000–$485,000 USD.

Company

Anthropic builds reliable, interpretable, and steerable AI systems designed to be safe and beneficial.

What you will do

• Design, build, and ship memory and search experiences across Claude.ai, Cowork, and Claude Code, owning work from backend services through model tools to user interfaces.
• Run product experiments by forming hypotheses, building demos, testing with users, measuring results, and making persevere-or-pivot decisions.
• Shape memory and retrieval within agentic loops, including storage decisions, search timing, result ranking, presentation, and user control.
• Define product metrics and evaluations for memory quality, improve search relevance and recall, and work with embeddings, hybrid retrieval, ranking, and result interfaces.
• Partner with product, design, privacy, legal, and safeguards on consent and enterprise requirements, including customer-managed encryption keys and data retention policies.
• Raise quality standards through design and code reviews, latency, polish, reliability, and shared on-call ownership.

Requirements

• Experience building and operating user-facing products used by a large number of people, including their backend services.
• Experience building agentic systems or LLM-powered products involving tool use, retrieval, and prompt or context design.
• Strong programming skills in Python and TypeScript, with experience across backend services and web front ends.
• Experience 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 for decision-making.
• Strong product judgment and the ability to explain why design choices matter to users.
• Strong written and verbal communication, including close collaboration with product managers, designers, and non-engineering partners.
• Interest in AI safety and Anthropic’s mission.
• Bachelor’s degree or equivalent education, training, and/or experience in a relevant field demonstrated through coursework, training, or professional experience.

Nice to have

• Experience as a founder, early-stage engineer, or product builder taking work from zero to one.
• Experience building search or retrieval systems, including embeddings, vector search, hybrid lexical and semantic retrieval, or ranking.
• Experience evaluating LLM or ML systems or measuring retrieval and ranking quality.
• Experience with high-retention consumer products or personalization systems.
• Experience shipping sensitive-data features or meeting enterprise requirements such as customer-managed encryption keys, data residency, or HIPAA.
• Experience with latency-sensitive, performance-critical product work.
• Experience mentoring engineers or setting technical direction for a team.

Culture & Benefits

• Collaborative work across research, engineering, policy, product, design, privacy, legal, and safeguards.
• Flexible working hours and a hybrid office policy.
• Competitive compensation, optional equity donation matching, generous vacation, and parental leave.
• Office space for collaboration and frequent research discussions.
• Visa sponsorship may be available, with immigration-lawyer support, depending on the role and candidate.