Senior Software Engineer

Lead validation of on-device AI models and experiences across Windows platforms and silicon partners.

Evaluate model accuracy, performance, power, scalability, and functional correctness across diverse hardware configurations.

Develop, enhance, and maintain validation frameworks, automation infrastructure, and performance analysis tools to support evolving AI model architectures.

Build solutions that enable efficient benchmarking and comparison of AI workloads across CPU, GPU, and NPU execution environments.

Analyze telemetry, traces, and validation data to identify regressions, bottlenecks, and optimization opportunities.

Collaborate with AI researchers, platform engineers, silicon partners, and product teams to ensure successful deployment of new AI capabilities on Windows.

Design automated quality gates and validation methodologies that scale across models, hardware platforms, and operating system releases.

Drive root-cause analysis and resolution of model accuracy, compatibility, performance, and reliability issues.

Mentor engineers and contribute to technical leadership within the team through design reviews, best practices, and knowledge sharing.

Establish guardrails and best practices for responsible use of AI tools—ensuring correctness, security, privacy, and compliance.

Improve test coverage and validation * Bachelor's or Master's degree in Computer Science, Electrical Engineering, Computer Engineering, or a related technical field. 8+ years of software engineering experience in systems, platform, validation, AI/ML infrastructure, performance engineering, or related domains.

Strong programming skills in C++, C#, Python, or related languages.

developing automation frameworks, validation infrastructure, or large-scale test systems.

Strong debugging and problem-solving skills with the ability to diagnose complex software and system-level issues.

analyzing performance, telemetry, profiling, or diagnostic data.

Ability to work independently and drive projects from concept to execution.

with AI/ML model validation, benchmarking, or deployment.

Familiarity with Windows AI, ONNX Runtime, DirectML, Windows ML, GenAI workloads, or model optimization techniques.

working with CPU, GPU, or NPU architectures and hardware acceleration technologies.

Knowledge of performance, power, thermal, or scalability analysis methodologies.

collaborating with silicon vendors or platform engineering teams.

Familiarity with model quality evaluation, benchmark development, and AI workload characterization.