Software Engineer II (Agentic AI)

Build agentic AI experiences for Microsoft’s sales organizations and help take promising ideas from prototype to production. In this Software Engineer II role, you’ll work with agent tooling, LLM-powered workflows, and integration with Microsoft sales systems to deliver capabilities that can be evaluated, hardened, and shipped.

You’ll be based in Redmond, WA (onsite) and supported by a team that values fast iteration, practical evaluation, and production readiness. The role is posted with a salary range of USD 102,100 - 219,200 per year.

What you’ll do

• Turn new agent ideas into working prototypes quickly, collaborating closely with a Principal engineer, PM, and design from the first demo through a seller pilot.
• Build agents, multi-step workflows, and Model Context Protocol (MCP) servers that connect to real seller and customer context in Dynamics 365, Dataverse, Microsoft Graph, and internal sales systems.
• Create reusable agent skills, tools, and plugins for Microsoft 365 Copilot and other agent hosts, contributing improvements back to a shared platform.
• Develop lightweight evaluations such as golden sets, LLM-as-judge scorers, and run traces, reporting quality, latency, and cost to guide scaling decisions.
• Harden prototypes that prove out using tests, telemetry, authentication, and Responsible AI review, supporting handoff to production surfaces like Sales Home.
• Document decisions with short design notes, demo progress to the team and leadership, and share learnings about new models and agent tooling.
• Participate in code and design reviews, and take part in on-call (DRI) duty for pilots and services you help ship.

What you bring

• Bachelor’s Degree in Computer Science or a related technical field, plus 2+ years of technical engineering experience with coding in languages including (but not limited to) C, C++, C#, Java, JavaScript, or Python, or equivalent experience.
• Ability to meet Microsoft, customer, and/or government security screening requirements, including passing the Microsoft Cloud Background Check upon hire or transfer and every two years thereafter.

Tools and technologies you may work with

You may use Azure OpenAI, Microsoft Foundry, Copilot Studio, Microsoft Agent Framework, MCP, Microsoft Graph, Dataverse, Dynamics 365, Teams, and Outlook, along with agent SDKs and frameworks including Microsoft 365 Copilot, Microsoft 365 Agents SDK, Semantic Kernel, AutoGen, and LangGraph. Development may include React and TypeScript, plus observability and integration tools such as OpenTelemetry and deployment across Azure, AWS, and GCP. Sales context may also involve systems such as Power Platform and Salesforce.

Preferred qualifications

• 4+ years of technical engineering experience (C#, TypeScript, JavaScript, Python, or Java) with a Bachelor’s Degree, or 3+ years with a Master’s Degree, or equivalent experience.
• Hands-on experience building applications with large language models, including prompt design, tool or function calling, retrieval-augmented generation, or agent frameworks.
• Experience building or integrating MCP servers, or exposing APIs and data to agents as tools.
• Experience with agent frameworks or platforms such as Microsoft Agent Framework, Semantic Kernel, AutoGen, Microsoft Foundry, Copilot Studio, Microsoft 365 Agents SDK, LangGraph, OpenAI Agents SDK, or Claude Agent SDK.
• A track record of building fast with hackathon projects, MVPs, demos, or internal tools that progressed to real users.
• Ability to work across the stack, including back-end APIs, a React/TypeScript front end, and deployments to Azure, AWS, or GCP.
• Experience evaluating LLM output using golden datasets, LLM-as-judge scoring, prompt or model comparisons, and tracing (for example with OpenTelemetry).
• Working knowledge of Responsible AI practices such as grounding, content safety, prompt injection defenses, and PII handling.
• Daily, fluent use of AI coding tools (for example GitHub Copilot, Claude Code, or Cursor) in a development workflow.
• Familiarity with Dynamics 365, Dataverse, Microsoft Graph, Power Platform, or CRM systems such as Salesforce, with an interest in sales or customer-facing products.