Principal Software Engineer Agentic Runtime & Orchestration

Job Description Join QAD as a Sr. Principal Software Engineer and be a visionary in defining and driving the technical strategy for the entire function. You will own complex, high-impact systems and directly contribute to the future of intelligent manufacturing. Your role will involve providing strategic technical direction, mentoring senior and principal team members, and leveraging your expertise in cloud-native architectures, microservices, and Agile product development to build the next generation of the platform. Your impact will be significant as you architect the agent orchestrator, design evaluation frameworks for agent behavior, own LLM Gateway architecture, define agent reliability standards, and set technical standards for agentic system design across the Agentic Platform sub-team. Key Responsibilities - Architect the agent orchestrator, including multi-step planning, tool dispatch, state machine, and error recovery - Design the evaluation framework for agent behavior, covering regression detection, model update validation, and eval pipelines - Own LLM Gateway architecture, focusing on model routing, cost governance, latency SLOs, and streaming response handling - Define agent reliability standards such as sandboxing, execution audit trails, timeout handling, and rate limiting - Set the technical standard for agentic system design across the Agentic Platform sub-team Qualifications - 10+ years in software engineering with expertise in AI systems engineering - Experience in shipping production LLM or agentic systems with real SLOs, failure modes, and post-mortems - Deep knowledge of agentic frameworks like LangGraph, AutoGen, or equivalent at the implementation level - Strong background in distributed systems, including async processing, state management, and reliability patterns - Experience in MCP (Model Context Protocol) design or implementation - Familiarity with hierarchical agent systems and multi-agent coordination patterns - Proficiency in responsible AI engineering practices, including agent guardrails, sandboxing, and human-in-the-loop design In this role, you will be a strategic problem solver with strong logical thinking and problem-solving abilities. You will need to adapt quickly to cutting-edge technologies, take ownership of architectural components, demonstrate a focus on quality, and exhibit proactive leadership qualities. Additionally, your ability to grasp new technologies, complex systems, and development methodologies rapidly will be crucial for success. Join QAD and benefit from structured mentorship programs, an inclusive culture that fosters learning and growth, and the opportunity to shape the future of manufacturing. Apply now to be part of a team that values diversity, equity, and inclusion, and is committed to creating a work environment where every employee can thrive. Job Description Join QAD as a Sr. Principal Software Engineer and be a visionary in defining and driving the technical strategy for the entire function. You will own complex, high-impact systems and directly contribute to the future of intelligent manufacturing. Your role will involve providing strategic technical direction, mentoring senior and principal team members, and leveraging your expertise in cloud-native architectures, microservices, and Agile product development to build the next generation of the platform. Your impact will be significant as you architect the agent orchestrator, design evaluation frameworks for agent behavior, own LLM Gateway architecture, define agent reliability standards, and set technical standards for agentic system design across the Agentic Platform sub-team. Key Responsibilities - Architect the agent orchestrator, including multi-step planning, tool dispatch, state machine, and error recovery - Design the evaluation framework for agent behavior, covering regression detection, model update validation, and eval pipelines - Own LLM Gateway architecture, focusing on model routing, cost governance, latency SLOs, and streaming response handling - Define agent reliability standards such as sandboxing, execution audit trails, timeout handling, and rate limiting - Set the technical standard for agentic system design across the Agentic Platform sub-team Qualifications - 10+ years in software engineering with expertise in AI systems engineering - Experience in shipping production LLM or agentic systems with real SLOs, failure modes, and post-mortems - Deep knowledge of agentic frameworks like LangGraph, AutoGen, or equivalent at the implementation level - Strong background in distributed systems, including async processing, state management, and reliability patterns - Experience in MCP (Model Context Protocol) design or implementation - Familiarity with hierarchical agent systems and multi-agent coordination patterns - Proficiency in responsible AI engineering practices, including agent guardrails, sandboxing, and human-in-the-loop design In this role, you will be a stra