Staff Software Engineer, AI Runtime

We’re seeking a Staff Software Engineer to help power the future of agentic AI workflows. You’ll take our MCP Server to the next level, turning it into an enterprise-grade service that lets diverse tools and systems be exposed effortlessly to AI agents. Looking ahead, you’ll also help architect the MCP Gateway—a new layer that will route requests across tools, enforce policies, and provide the runtime foundation for scalable multi-agent systems. Along the way, you’ll tackle challenges in scalability, performance, and developer experience to ensure our platform feels seamless, powerful, and enterprise-ready.

About the Team

The Graph DX AI Runtime Team builds and maintains the MCP Server and Gateway—the backbone of agent-to-tool communication and the routing layer that keeps everything flowing. We make it simple for developers to wire up agents, orchestrate workflows, and scale interactions reliably. Our focus is on speed, security, and seamless integration, so teams can spend less time managing infrastructure and more time building intelligent experiences.

• Architect and scale an enterprise AI/MCP Server and Gateway that powers multi-agent workflows across Apollo, including routing, orchestration, and integration boundaries.
• Design and implement robust server infrastructure to ensure reliability, performance, and security at scale.
• Build and maintain tools for agent discovery, communication, and coordination.
• Define deployment strategies and runtime optimizations to maximize efficiency and minimize operational overhead.
• Develop frameworks and patterns that enable seamless multi-agent collaboration and AI-driven orchestration.
• Integrate observability, logging, and monitoring for full visibility into server and agent behavior.
• Explore and implement AI-enhanced developer workflows to optimize orchestration and agent interactions.
• Collaborate with teams across Apollo to ensure the MCP Server meets evolving product and developer needs.

• Architect and scale the MCP Gateway—Apollo’s routing layer for agentic workflows—ensuring tools and services can be discovered, invoked, and orchestrated reliably across diverse environments.
• Design and implement high-performance routing infrastructure with reliability, scalability, and security at its core.
• Build and maintain routing patterns and coordination mechanisms that let agents interact with the right tools at the right time.
• Define deployment strategies and runtime optimizations to minimize latency and operational overhead.
• Explore and implement AI-driven routing strategies to optimize context retrieval, reduce cost, and improve decision accuracy.
• Collaborate with teams across Apollo to ensure the MCP Server and Gateway integrate seamlessly with Apollo’s control plane for AI tools.
• Integrate observability and monitoring into the routing layer to provide full visibility into traffic flows, tool availability, and agent interactions.

• Expertise in agent-to-tool orchestration, routing, and coordination in scalable, fault-tolerant systems.
• Strong background in distributed systems, server architecture, and high-performance backend development.
• Proven experience with protocol design, message routing, and server-side orchestration frameworks.
• Experience building and maintaining robust runtime infrastructure that supports AI-driven workflows and enables reliable agent-to-tool interactions.
• Proven experience with protocol design, message routing, and building server-side frameworks that enable scalable, reliable multi-tool agent workflows.
• Hands-on experience with observability, monitoring, and debugging frameworks for complex systems.
• Passion for clean, maintainable code, high system reliability, and scalable architecture.
• Experience in strategic system design, making architectural trade-offs, and planning for long-term scalability and maintainability.
• Strong technical leadership and mentorship, including guiding junior engineers and driving engineering best practices across teams.
• Ability to influence cross-team architecture decisions and align engineering efforts with product and business objectives.
• Production ownership experience: leading incident response, debugging, and performance optimization in high-impact backend systems.

• Exposure to AI/ML-enabled developer tooling or autonomous system orchestration.
• Familiarity with cloud-native architectures, containerization, or orchestration frameworks.
• Experience with performance optimization and cost-efficient scaling of high-throughput distributed systems.

At Apollo, we strive to provide competitive, market-informed compensation whilst ensuring consistency within the team in each country. We make hiring decisions based on your skills, experience, and our overall assessment of what we learned during the hiring process. In addition to the U.S. base salary range, we also provide equity and benefits.

Apollo offers all U.S. employees a choice of 3 Anthem Blue Cross medical plans and California residents can also choose from an additional 2 Kaiser medical plans. Dental and Vision benefits are provided by Sun Life Financial.

Location: This is a remote position that can be done from anywhere in the United States or Canada.

Equal Opportunity: Apollo is proud to be an equal opportunity workplace dedicated to pursuing and hiring a talented and diverse workforce.

Privacy: California residents applying for positions at Apollo can see our privacy policy here.

E-Verify: Apollo is an E-Verify employer and will provide the federal government with your Form I-9 information to confirm that you are authorized to work in the U.S. For more information, please visit E-Verify.