Overview
As a Software Engineer II in Agentic Engineering Productivity, you will build LLM-powered agents that turn intent into tested, reviewable changes, keep build pipelines and internal tools healthy, and help drive cross-team initiatives from plan to delivery. You will work with teams across infrastructure, security, and product services, owning your area from end to end. This individual-contributor role combines hands-on development with practical judgment about what to automate and where people stay in control. Success means verified engineering outcomes, not simply more generated code. You will use measures such as validated task completion, review usefulness, human intervention and rework, cycle time, defects, and build pipeline health to guide decisions, and keep stakeholders informed of status and risks. 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.
Responsibilities
Agentic engineering
- Build and maintain agent capabilities in your feature area that carry authorized work through implementation, test execution, code review, and remediation. Produce pull requests with attributable changes and evidence of what was checked, what passed, and what still needs to be reviewed.
- Design orchestration steps, tool integrations, and context retrieval for real repositories, build and test systems, and CI pipelines. Weigh design options and trade-offs, and build well-defined interfaces, durable state, and monitoring from the start.
- Write LLM and agent evaluations and regression tests grounded in engineering tasks. Debug failures across models, prompts, context, and tools to their root cause, and use results to qualify changes before they ship.
- Implement secure, bounded execution with scoped permissions, explicit approval for privileged actions, and human review before changes are accepted. Make agent actions observable and attributable, with stop conditions when authorization or evidence is insufficient.
Engineering systems and operations
- Monitor and maintain build pipelines for engineering systems, investigate and troubleshoot infrastructure-related build failures, engage partner teams on other failures, and help internal teams integrate with pipeline components.
- Provide IcM support for the services the team owns and serve as an escalation point during outages and investigations.
- Collaborate with other teams to surface the health and hygiene of engineering systems through monthly service reviews, and stay engaged in security and services infrastructure initiatives, including geo expansion of team-owned services.
- Administer internal tools: manage permission structures, deploy technology upgrades to existing systems, and help implement new technology as it becomes available. Continually strengthen tool administration and documentation and process improvements from idea to completion.
Execution and stakeholder partnership
- Define requirements and acceptance criteria with input from key stakeholders, help inform feature priorities, and partner with solution engineers to validate that designs meet or exceed business needs.
- Drive engineering initiatives across teams: break loosely defined work into well-scoped tasks, build timelines and level-of-effort estimates, manage milestones, identify and mitigate execution risks, course-correcting to hold schedules.
- Bring clarity to roadmaps, status, and risks through regular reporting, engineering newsletters, and other forums, and automate program management with Azure DevOps, GitHub, and Power BI.
- Coordinate release plans, communications, testing, and change management with business and engineering teams for larger features. After release, compare results against meaningful baselines to verify that solutions capture the benefits identified during planning.
Qualifications
Required 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.
Other Requirements:
Ability 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:
- Master's Degree in Computer Science or related technical field AND 3+ years technical engineering experience with coding in languages including, but not limited to, C, C++, C#, Java, JavaScript, or Python
- OR Bachelor's Degree in Computer Science or related technical field AND 5+ years technical engineering experience with coding in languages including, but not limited to, C, C++, C#, Java, JavaScript, or Python
- OR equivalent experience.
- Solid software engineering fundamentals, with proficient coding, debugging, and automated testing in C# or C++, and working knowledge of big data, ML, NLP, or search technologies.
- Hands-on experience building LLM-powered features, applications, or agents that use tools or execute multi-step workflows, beyond personal use of AI coding assistants.
- Ability to debug and improve LLM or agent behavior using task-level tests, traces, and failure analysis, and to distinguish plausible model output from correct, reproducible engineering results.
- Background in cloud services or DevOps, including building and supporting features in distributed systems with working knowledge of state management, observability, security, and reliability.
- Experience using Azure DevOps and GitHub for project tracking, or the technical acumen to learn new technologies quickly.
- A record of independently delivering features from design to production, along with solid analytical skills and experience in customer engagement and cross-functional collaboration.
- Exposure multi-agent coordination, durable workflow execution, or recovery from interrupted and partially completed agent tasks.
- Familiarity with repository-aware context retrieval, code understanding, or model routing and fallback, including trade-offs between quality, latency, and cost.
- Experience contributing to developer tools, build and test infrastructure, CI integrations, automated code review, or repair workflows, and comfort with the command line, PowerShell, and open-source software.
- Experience supporting adoption of AI-powered engineering workflows or running evaluations and experiments that connect agent use to measured engineering outcomes.
- Understanding cloud, AI, and other computing technologies, including their business drivers and emerging trends inside and outside Microsoft.
- A hands-on engineer at heart, with prior software development experience and a passion for cloud technologies and AI.
- Track record of working closely with agile, diverse, and geographically dispersed engineering teams, and of building relationships with senior technical and business leaders.
- A self-starter who likes tackling new challenges and working independently, with strong verbal and written communication skills, including fluency in English.
#CAP #Agent365 #A365
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.
Microsoft is an equal opportunity employer. All qualified applicants will receive consideration for employment without regard to age, ancestry, citizenship, color, family or medical care leave, gender identity or expression, genetic information, immigration status, marital status, medical condition, national origin, physical or mental disability, political affiliation, protected veteran or military status, race, ethnicity, religion, sex (including pregnancy), sexual orientation, or any other characteristic protected by applicable local laws, regulations and ordinances. If you need assistance with religious accommodations and/or a reasonable accommodation due to a disability during the application process, read more about requesting accommodations.