Senior Software Engineer (Windows ML MLIR Platform)

Microsoft•Redmond, WA

7d•$119,800 - $261,000•Hybrid

About The Position

Help define how AI runs on Windows at global scale. The Windows AI Platform & Tools Team is building the foundational software that turns rapidly advancing models and silicon into fast, efficient, and trusted experiences for millions of customers. Working at the intersection of machine learning compilers, runtimes, operating systems, and heterogeneous hardware, you'll collaborate across Microsoft and with leading silicon partners to solve consequential edge-AI systems challenges. As a Senior Software Engineer, you will design and deliver core capabilities for the Windows ML MLIR platform across CPU, GPU, and NPU hardware. You will work on production compiler and runtime components that enable developers to deploy machine learning models efficiently and reliably, contributing to graph compilation, hardware-aware optimization, scheduling, memory orchestration, power efficiency, and secure execution. You will own complex features end to end, collaborate across team boundaries, and help turn emerging model and hardware capabilities into durable Windows platform building blocks. The role offers flexible work options, including partial remote work. In alignment with our Microsoft values, we are committed to cultivating an inclusive work environment for all employees to positively impact our culture every day. 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.

Requirements

Bachelor's Degree in Computer Science or related technical field AND 4+ years 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 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.

Nice To Haves

Master's Degree in Computer Science or related technical field AND 6+ 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 8+ years technical engineering experience with coding in languages including, but not limited to, C, C++, C#, Java, JavaScript, or Python.
OR equivalent experience.
Experience with MLIR, LLVM, ONNX Runtime, or comparable compiler and runtime technologies.
Experience optimizing machine learning workloads for CPU, GPU, NPU, or other heterogeneous hardware.
Knowledge of machine learning inference, graph compilation, memory management, and performance analysis.
Experience building local model integrations in system- or application-level components.
Experience developing and debugging production software in modern C++.
Experience with systems software, compilers, runtimes, machine learning infrastructure, or performance-critical platform components.
Demonstrated ability to design, implement, test, and operate complex software features across team boundaries.

Responsibilities

Collaborates with and guides appropriate internal (e.g., product manager, privacy/security subject matter expert, technical lead) and external (e.g. customer escalation team, public forums) stakeholders to determine and confirm customer/user requirements for a project/sub-section of a product/solution. Incorporates customer insights into future designs or solution fixes. Ensures unwritten requirements, such as appropriate continuous feedback loops that measure actionable, quantitative (e.g., customer value, usage patterns, solution performance) and qualitative (e.g., accessibility, globalization) indicators of value are incorporated. Understands, provides feedback on, and advocates for security and privacy needs of the customer who will be using the project/sub-section of a product/solution.
Identifies dependencies and incorporates them into the development of design documents for a product, application, service or platform. Actively identifies other teams and technologies to leverage, how they interact, and where their own system or team can support others. Understands upstream and downstream interactions between systems and ensures security, compliance, performance, and reliability can be achieved across the entire stack. Collaborates with other teams to reach common goals where dependencies and validation concerns overlap. Works across teams to resolve conflicts around dependency ownership and required work.
Leads by example within the team to produce extensible, maintainable, well-tested, secure, and performant code that adheres to design specifications. Continuously improves code performance, testability, maintainability, effectiveness, and cost, while learning about and accounting for relevant trade-offs. Applies metrics to drive code quality and stability. Applies appropriate coding patterns and best practices (e.g., leveraging state-of-the-art generative artificial intelligence [GenAI], approaches to source code organization, naming conventions). Identifies and escalates blockers or unknowns during the development process, communicates how they will impact timelines, and identifies strategies and/or opportunities to address them.
Leverages their subject-matter expertise to partner with appropriate stakeholders (e.g., technical program managers) to drive a workgroup's project plans, release plans, and work items. Organizes work into smaller sets of tasks as part of an overall roadmap. Guides other members for project estimation and escalates issues that might cause a delay. Ensures required security protections and detection processes are accounted for in planning. Ensures project plans adhere to security, privacy, and compliance requirements. Ensures all code for a product/solution is properly flighted for quicker mitigation of production incidents. Calculates capacity for planning, accounting for appropriate failover and backup/restore mechanisms for disaster recovery for a project/sub-system of a product. Makes considerations for efficient operation of a project/sub-system of a product after it is live. Establishes a rollback plan for a project/sub-system of a product.
Acts as a designated responsible individual (DRI) and guides other engineers by developing and following the playbook, working on-call to monitor a system/product/service for degradation, downtime, or interruptions. Alerts stakeholders as to status and initiates actions to restore system/product/service for simple problems and complex problems when appropriate. Responds within service level agreement (SLA) timeframe. Drives efforts to reduce incident volume, looking globally at incidences and providing broad resolutions. Escalates issues to appropriate owners.
Remains current in skills by investing time and effort into being informed of current developments. Proactively seeks new knowledge, evaluating new trends, technical solutions, and patterns, assessing how to adapt them to current problems. Conducts learning and literary sessions to raise awareness on relevant engineering design principles (e.g., security, testability, performance, scalability, accessibility, product knowledge).
Design, implement, test, and support production-quality compiler and runtime features for the Windows ML MLIR platform.
Optimize model execution across CPU, GPU, and NPU hardware, including graph transformations, operator lowering, memory use, scheduling, and performance analysis.
Own complex features from design through deployment, using telemetry and disciplined engineering practices to improve reliability, diagnosability, and efficiency.
Collaborate with Windows, model, runtime, and silicon-partner engineers to integrate new capabilities and resolve end-to-end performance and compatibility issues.