Required Skills
About the Job
Join the Azure AI Inferencing team, a critical part of our CoreAI Foundry business. We build and operate the model-serving platform that powers billions of requests daily for massive-scale AI, including large OpenAI generative models. This is your opportunity to be at the forefront of AI innovation, supporting every Azure OpenAI customer and scenario, from internal products like Bing and Office to third-party applications.
We are seeking a highly experienced Software Engineer passionate about designing and building exceptionally reliable and available platforms for high-throughput, low-latency AI inference. You will drive performance optimization and solve complex challenges at the intersection of AI and Cloud. Microsoft's ambitious mission is to democratize AI, making it an essential component for breakthrough customer experiences and ensuring its safe and responsible application globally. Our culture fosters a growth mindset, encouraging daily contributions from all team members.
**Responsibilities:**
- Lead the architecture and design of complex, distributed systems.
- Make critical technical decisions and mentor engineers on design tradeoffs and best practices.
- Ensure end-to-end solution quality, including test strategy, security testing, reliability, and operational readiness.
- Drive cross-team collaboration, manage dependencies, and align delivery plans.
- Serve as the DRI for live systems, leading incident response, root-cause analysis, and proactive improvements.
- Champion security, privacy, compliance, and Responsible AI principles.
- Lead automation and deployment excellence for scalable, zero-touch deployments with safe rollout strategies.
- Elevate engineering standards through code reviews, telemetry, performance enhancements, and mentorship.
