Drimva

Anthropic

Staff Software Engineer, Claude Code

$320K–$625K

San Francisco, CA +3 · Staff · Full-time · Posted Aug 7, 2026

Location
San Francisco, CA
New York City, NY
Seattle, WA
San Francisco, California, United States
Experience
6+ years of work experience; logistics also says required years correlate with internal job-level requirements.
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 guaranteed for every role or candidate; if an offer is made, Anthropic will make every reasonable effort to obtain a visa.

About the job

Build and maintain agentic coding tools and infrastructure, improving developer experience and collaborating with researchers on model capabilities and evaluations.

What you'll do

  • Design, build, and maintain scalable features and infrastructure for AI-powered development tools.
  • Gather developer feedback and collaborate with researchers on tools and evaluations to improve model capabilities.
  • Develop features across the stack, fix bugs, optimize performance, and assess new AI-assisted coding techniques.

What they ask for

  • Expert React development, including performance optimization, modern patterns, and component architecture.
  • Hands-on experience with large language models and prompt engineering.
  • Experience building and maintaining developer tools.
  • 6+ years of work experience.

Nice to have

  • Experience building and maintaining CLI tools, working in large codebases, or entering unfamiliar development environments.
  • Experience with container orchestration, cloud infrastructure, scaling TypeScript projects, Bun, or Deno.

Pay

$320,000 — $625,000 USD (base salary)

Tools

React, Python, VS Code, TypeScript, Bun, Deno

AI focus

Build AI-powered agentic coding tools; work with LLM features and prompt engineering, and collaborate with researchers to improve model capabilities through tools and evaluations.

Model-written summary · the original posting is authoritative

First seen Oct 8, 2026 · Last verified Nov 4, 2026 (UTC)