Software Engineer 2 - CoreAI

Within Microsoft CoreAI, the Azure SRE Agent Platform team builds and operates production AI agents that help engineers detect, diagnose, and mitigate reliability issues across Azure services and customer workloads. Our work turns modern AI systems into reliable, production-grade operational tooling for AI ops scenarios, with a focus on quality, safety, and real-world impact. 

We are looking for a Software Engineer 2 - CoreAI to help build the next generation of agentic systems for cloud operations. This role is for engineers who care deeply about product quality, end-to-end ownership, and the details that separate an exciting prototype from a system people trust during critical moments. 

Our work spans the full lifecycle of agentic systems in production. We design and improve the core capabilities that shape agent behavior, including tool design, planning and execution loops, orchestration, evaluation, and safety guardrails. We also build the operational foundations that make those systems dependable in practice, including observability, progressive delivery, reliability engineering, and live-site learning. 

Engineers on this team operate with high autonomy in a highly agile environment: short cycles, thin slices, feature flags, progressive delivery, and constant learning. We are looking for people with high agency and a bias for action - engineers who take ownership of ambiguous problems, move quickly, learn from production, and continuously raise the quality bar as they ship. 

Microsoft’s mission is to empower every person and every organization on the planet to achieve more. As employees, we come together with a growth mindset, innovate to empower others, and collaborate to realize our shared goals. Each day, we build on our values of respect, integrity, and accountability to create a culture of inclusion where everyone can thrive at work and beyond. 

• Take ownership of important areas of the Azure SRE Agent Platform, including agent capabilities, orchestration, evaluation, and supporting platform services.
• Build and iterate on agentic systems, including tools, planning and execution loops, evaluations, and safety mechanisms.
• Design and ship reliable capabilities that improve incident detection, diagnosis, mitigation, and operational learning.
• Use telemetry, experiments, evaluations, and user feedback to guide iteration and investment.
• Contribute to resilient, observable systems that operate safely and effectively in production.
• Partner closely with engineers, SREs, and product counterparts to turn ambiguous problems into high-quality shipped solutions.
• Participate in debugging, live-site learning, and post-incident hardening to continuously improve system quality.
• Contribute to architecture, engineering standards, and development practices across the team.

Required/Minimum Qualifications:

• Bachelor's Degree in Computer Science or related technical field AND 2+ years technical engineering experience with coding in languages including, but not limited to, C, C++, C#, Java, JavaScript, or Python
  • OR equivalent experience? 

• Microsoft Cloud Background Check: This position will be required to pass the Microsoft Cloud background check upon hire/transfer and every two years thereafter.

Preferred/Additional Qualifications: 

• Bachelor’s Degree in Computer Science or related technical field AND 4+ years of technical engineering experience with coding in languages including, but not limited to, C, C++, C#, Java, JavaScript, Go, or Python
• 3+ years of experience building and operating cloud platforms or distributed services, with depth in service architecture, deployment, and observability
• Hands-on experience building and operating generative AI or agentic systems in production, with direct ownership over quality, reliability, and iteration
• Product mindset with a track record of owning ambiguous problem spaces and driving them to high-quality outcomes
• Solid engineering fundamentals, including systems design, performance, and debugging in complex production environments
• Experience designing, running, and optimizing evaluations for agentic systems, including tools, prompts, and agent loops
• Experience with Kubernetes, container orchestration, or cloud-native infrastructure is a plus 
• Experience contributing to or leading open-source projects on a scale is a plus