OverviewAs a
Software Engineer, you will design and ship core components of the Agentic support platform that Microsoft support relies on daily. You own features end to end, from prototype to production, working across orchestration, grounding, evals, observability, and the SDK surfaces other engineers build on. You take real ownership of what you ship, help raise the bar for how agents are built and evaluated on the team, and grow your influence as you go.
This role is for an engineer with a strong bias for action who will be responsible for designing, operating, and evolving AI-driven, end-to-end autonomous support workflows that are foundational to Microsoft's next-generation Support experience. The role sits at the intersection of AI engineering, live-site operations, compliance, and business transformation, ensuring that AI-managed support systems are production-ready, trustworthy, and scalable.
Responsibilities- Build agentic workflows using frameworks like Azure AI foundry, Microsoft Copilot studio or equivalent.
- Owning the run-state reliability of AI-driven support workflows, including incident response, live-site health, and continuous tuning.
- Implementing AI workflows to changing support business policies and operational processes (e.g., SLA calculations, case ownership, escalation models).
- Driving customer trust, satisfaction, and sentiment, ensuring AI agents correctly understand intent and guide customers to resolution without degrading experience.
- Ensuring security, privacy, and responsible AI compliance, including rethinking role-based access control (RBAC), data access, case ownership vs. processing, and data exposure.
- Implementing observability, monitoring, and intervention mechanisms for multiple AI agents operating concurrently.
- Contributing to the delivery of a platform that enables citizen developers to safely build AI agents for support workflows with reduced barrier to entry.
QualificationsRequired/minimum qualificationsBachelor'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.
Other QualificationsAbility to meet Microsoft, customer and/or government security screening requirements are required for this role. These requirements include but are not limited to the following specialized security screenings: 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 Qualifications - Experience building LLM-powered applications, RAG pipelines, prompt engineering, agent frameworks (Semantic Kernel, LangChain), or fine-tuning with an eye for evaluation, latency, and cost.
- Proficiency in AI-native development working within Agent Harnesses (GitHub Copilot CLI, Coding Agents), authoring Markdown specs/ADRs and YAML configs as Agent-consumable inputs, orchestrating multi-step Agentic workflows across the SDLC, and reviewing Agent-generated code and PRs with production-grade rigor.
- Experience shipping agent-based systems in production, including hands-on experience with evals, observability, and debugging.
- Experience standing up evals or observability for non-deterministic systems.
- Experience contributing to the safety posture of AI systems, including prompt-injection defences and audit trails.
- Experience owning and shipping significant features end to end.
Software Engineering IC3 - The typical base pay range for this role across the U.S. is USD $102,100 - $202,200 per year. There is a different range applicable to specific work locations, within the San Francisco Bay area and New York City metropolitan area, and the base pay range for this role in those locations is USD $133,800 - $219,200 per year.
Certain roles may be eligible for benefits and other compensation. Find additional benefits and pay information here:
https://careers.microsoft.com/us/en/us-corporate-pay
This position will be open for a minimum of 5 days, with applications accepted on an ongoing basis until the position is filled.
