Principal SWE Lead

prompts, models, tools, orchestration flows, and system integrations. Validate quality and readiness. Evaluate groundedness, accuracy, task completion, robustness, latency, cost, safety, and failure modes at each deployment milestone in partnership with TPMs and support-domain experts. Deliver enterprise-ready solutions. Define measurable outcomes. Establish success metrics and telemetry that demonstrate customer value, support effectiveness, engineering health, operational readiness, and suitability for scale. Drive operational excellence. Create monitoring, incident response, debugging, and continuous-improvement mechanisms for AI systems in production. Influence across organizations. Partner with senior leaders and cross-functional teams to align priorities, manage technical tradeoffs, and deliver strategic initiatives spanning multiple organizations. Grow engineering capability. Mentor engineers, raise the technical bar, promote thoughtful experimentation, and build a culture of

inclusive collaboration, knowledge sharing, and high-quality execution. Document for long-term success. Maintain clear architecture, design decisions, limitations, evaluation evidence, deployment guidance, and operational runbooks. Bachelor’s Degree in Computer Science or related technical field AND 6+ years technical engineering experience with coding in languages including, but not limited to, C, C++, C#, Java, JavaScript, or Python OR equivalent experience Master’s Degree in Computer Science or related technical field AND 8+ years technical engineering experience with coding in languages including, but not limited to, C, C++, C#, Java, JavaScript, or Python OR Bachelor’s Degree in Computer Science or related technical field AND 12+ years technical engineering experience with coding in languages including, but not limited to, C, C++, C#, Java, JavaScript, or Python OR equivalent experience. Hands-on experience building applied AI systems, including generative AI, large language models, or autonomous agents. 10+ years of professional software design and development experience, including architecture and delivery of complex production systems. Experience designing, building, deploying, and operating highly available, secure, and scalable cloud services Strong proficiency in one or more modern programming languages, with the ability to contribute directly to production code; experience with Python is highly relevant. Experience with distributed systems, APIs, data platforms, observability, testing, and production operations. Strong communication skills and the ability to explain complex technical decisions to engineering, product, business, and executive audiences. Experience with Azure AI Foundry, Copilot Studio, Power Platform, Azure services, or comparable enterprise AI and cloud platforms. Deep expertise in one or more of the following: agent platforms, multi-agent orchestration, retrieval-augmented generation, knowledge systems, AI evaluation, prompt engineering, model selection, or ML infrastructure. Exerience developing evaluation frameworks and quality gates for generative AI, including groundedness, safety, robustness, and task-success measurement. Experience integrating AI solutions with enterprise systems, security boundaries, identity, data governance, and compliance controls. Experience building AI-powered diagnostics, customer support, service operations, or workflow automation solutions.

Architect and build production-grade AI systems. Design, implement, and operate agentic AI solutions, diagnostic experiences, orchestration workflows, and supporting platforms using governed ProCode and citizen-development technologies where appropriate. Set technical direction. Define architecture, engineering strategy, design principles, and reusable patterns for AI solutions that must operate securely and reliably at enterprise scale. Lead through code and engineering rigor. Develop critical components, conduct design and code reviews, establish testing standards, and resolve the most complex technical and architectural issues. Integrate with the support ecosystem. Advance agent orchestration and diagnostics. Solve difficult problems in planning, context and state management, tool use, multi-agent coordination, retrieval, grounding, observability, and failure recovery. Build robust evaluation capabilities. Establish technical, unit, integration, regression, and end-to-end testing for