Responsibilities
'• Analyze data signals and uncover patterns: analyze support-case trends, customer issue patterns, and authorized technical signals at scale to uncover recurring failure patterns and gaps in Azure diagnostics and documentation. Design and build production AI services: Develop scalable agentic AI solutions for Azure diagnostics and documentation using LLM orchestration, RAG pipelines, agent workflows, tool integrations, memory and state management, and human-in-the-loop experiences, Lead through hands-on engineering: Write, review, test, and maintain production-quality C# and Python code. Build reusable components, reference implementations, and engineering patterns that accelerate team delivery. Own end-to-end technical delivery: Translate customer support scenarios and product requirements into technical designs, then take solutions through implementation, testing, deployment, monitoring, and continuous improvement. Build evaluation-driven AI systems: Develop evaluation frameworks using rubrics, golden datasets, simulations, judge models, and offline and online evaluation. Use measurable quality thresholds to guide agents from experimentation toward production operation. Engineer for production quality: Ensure services meet requirements for correctness, reliability, availability, latency, scalability, maintainability, cost, and safety. Implement secure and responsible AI patterns: Apply privacy protections, prompt-injection defenses, least-privilege tool access, identity and authorization controls, data boundaries, approval gates, auditability, and fail-safe behavior. Integrate with Azure services and data sources: Ground agent responses and actions in trusted, current signals by integrating with Azure data sources, APIs, and cloud-native services. Operate services in production: Implement CI/CD, automated testing, feature flags, staged rollouts, tracing, logging, metrics, and alerting. Diagnose production issues, participate in incident response, and drive corrective improvements. Make evidence-based technical decisions: Evaluate models, frameworks, prompts, retrieval approaches, and architectural options using experiments and production telemetry. Balance quality with reliability, latency, cost, maintainability, and operational complexity. Drive measurable customer impact: Instrument solutions and use data to improve automation quality, case-volume reduction, resolution time, engineering efficiency, and customer satisfaction. Provide technical leadership within projects: Lead design reviews, resolve technical challenges, coordinate implementation across contributors, and align partner teams around shared interfaces and delivery goals. Mentor and raise engineering capability: Support other engineers through code reviews, technical guidance, reusable documentation, and practical coaching in applied AI and production software engineering. Collaborate across organizational boundaries: Partner with product managers, researchers, platform engineers, Azure service teams, and support-domain experts to deliver durable solutions and shape future platform capabilities.