Staff Software Engineer (AI Pod)
Summary
Builds and maintains Toast’s internal AI platform, including an LLM proxy, autonomous agents for SDLC, and MCP integrations, while mentoring engineers and driving adoption of agentic development practices.
- As a Staff Software Engineer on this team, you'll shape the foundation others build on: from the LLM Proxy that routes all internal AI traffic, to autonomous agents that participate directly in the software development lifecycle.
- Design, build, and ship core AI platform infrastructure, including the LLM proxy, AI key management, and observability pipelines powering Toast's internal AI ecosystem
- Architect and deliver autonomous agents that participate in the SDLC, including the AI Review GitHub App and Developer Platform MCP integrations
- Build on and help maintain the internal plugin marketplace, developing plugins that encode Toast's architectural standards, PR patterns, and quality practices directly into AI assistant behavior
- Lead technical design and implementation of MCP (Model Context Protocol) services and no-code service templates that accelerate AI-powered development across Toast
- Drive adoption of agentic development practices through tooling, internal evangelism, and hands‑on enablement across engineering teams
- Mentor engineers through code reviews, architecture discussions, and pairing sessions
- Partner with product and platform teams to define and expand the AI Foundations roadmap
Benefits
- Peer and company recognition programs
- Unlimited Vacation
- Sabbatical opportunity after five years
- Professional Development Reimbursement Program
- Commitment to Employee Wellness through resources such as a quarterly Wellness Stipend
- Various peer and company recognition programs
- 401(k) and matching
- Medical, Dental, & Vision Coverage
- Subsidized backup childcare
- Mental Health Benefits
Requirements
- Experience with distributed systems, API design, and cloud-native infrastructure
- Demonstrated experience building, deploying, or operating LLM-powered agents or AI-assisted developer tooling
- Deep familiarity with AI coding assistants (e.g., Claude Code, Cursor, GitHub Copilot) and the ability to extend them through custom plugins, skills, or hooks
- Strong prompt engineering skills and intuition for how LLM behavior changes with context, instructions, and tool definitions
- 8+ years of experience designing and implementing scalable backend services
- Hands‑on experience with MCP (Model Context Protocol), tool use patterns, or agentic frameworks
- Strong customer empathy and the ability to translate developer pain points into platform solutions
- Strong foundation in Java, Kotlin, or another object‑oriented language, with experience building scalable backend services
- Proven track record of technical leadership: influencing architecture decisions, setting quality standards, and mentoring peers
- Familiarity with A2A (Agent-to-Agent) protocols and multi-agent orchestration patterns
- Experience with machine learning concepts, model evaluation, or ML infrastructure
- Experience building developer experience platforms, internal tooling, or API gateways
- Familiarity with observability tooling for AI/LLM systems (e.g., Langfuse, DataDog)