Senior Software Engineer

Start Date: ASAP Role Type: Full-Time, Salaried Background: Software development Location: Remote,Flexible (USA based) Salary: $160,000-$190,000 per year, plus benefits Who We Are: The Keystone AI (MCP) is a 501(c)(3) nonprofit organization that empowers educators to build classrooms that respond to every student’s needs. Founded by two award-winning teachers, we lead a movement of educators in implementing a self-paced, mastery-based instructional model that leverages technology to foster human connection, authentic learning, and social-emotional growth. To date, we have reached over 100,000+ teachers through our free online course in 150+ countries. We are an ambitious, idealistic team led by former classroom teachers, and we are passionate about what we do. Job Description - Why we need you! For the past eight years, we have empowered educators to use technology more effectively. Last year, we secured funding to begin developing our own edtech software products. We need an experienced, hands-on, AI-native Senior Software Engineer to help transform our product vision into reality. You will be a foundational member of our new technical team, taking the lead on back-end and generative AI content pipelines, and creating intuitive, powerful tools that will directly support educators and students every day. Key Responsibilities As Senior Software Engineer, you will be a senior individual contributor on our engineering team, reporting to the Head of Engineering and collaborating closely with the Chief Innovation Officer to ship features that make a real difference for students and educators. You’ll be joining a small and growing team of talented software engineers working together to solve the problems our teachers face every day, make teachers more effective, and make our evidence-based model more accessible to any educator who wants to help all of their students succeed. We need you to help us make that happen. You will: Ship multiple substantial features per week. This is a minimum velocity bar, not an exaggeration. You will leverage AI and agentic coding to build incredible software, very, very quickly. Operate as the technical lead and steward of your agentic coding pipeline. Write detailed prompts and specifications, and embrace Spec-Driven Development. Compose orchestrator agents and dispatch agent teams. Engineer RALPH Loops with well-formed completion promises. Actively multitask between several agents to simultaneously develop multiple substantial features in parallel. Build the AI workflow engine that powers our products. Develop state-of-the-art graph-based agentic orchestration workflows with nodes and conditional edges, structured outputs, interrupts and human-in-the-loop circuit breakers. Implement durable execution, long-running work that survives process restarts, rate limits, and outages, with an evaluation harness, versioned prompt chains, annotated datasets and cross-provider benchmarks on cost, latency, and quality. Architect resilient, high-scale backend systems. Design and scale distributed infrastructure across Python and TypeScript to support heavy edtech workloads. Own the systems design, API boundaries, and database performance, ensuring that our foundational architecture remains highly available, secure, and ready to scale. Extend the context layer. Contribute to our AGENTS.md and Agent Skills so that every session produces better work than the last. These are living production artifacts, and you own the parts that describe your domain. Partner on architecture. Collaborate closely with the Head of Engineering, Chief Innovation Officer, and other product leaders on technical direction, feature roadmap, and the hard technical design decisions and trade-offs underneath. Raise the bar for the team. Review the work of teammates and contractors. Collaborate with teammates on architecture and implementation reviews. Write PR comments, design docs, and agent skills that make the next person faster. You should apply if: You are AI-native. You are an expert in continuous multi-session development with Claude Code and/or OpenAI Codex. You are an expert at prompt engineering and context engineering. You write Agent Skills the way other engineers write unit tests. You practice Spec-Driven Development (GitHub Spec Kit or equivalent) as part of your normal workflow. You know what a RALPH Loop is and how to deploy one. You ship, a lot. You deliver multiple large features per week. Not because you're cutting corners, but because you've rebuilt your workflow around agentic tools and you have the taste to steer them well. You know the difference between vibe-coding and prompt engineering with specification-driven work, and you know which one to reach for in which situation. You have built real backend AI orchestration layers that run when you're not watching. You think in graphs — shared state flowing through nodes, conditional edges, interrupts, and circuit breakers. You have shipped non