Senior and/or Principal Software Engineer- LLM Serving Performance

Microsoft•Redmond, WA

7d•$119,800 - $304,200

About The Position

The Microsoft AI Frameworks team develops the software and systems that enable state-of-the-art AI models to run reliably and efficiently at cloud scale. We work across model architectures, frameworks, compilers, runtimes, libraries, and hardware platforms—including NVIDIA and AMD GPUs and Microsoft silicon. We are seeking hands-on Senior and/or Principal Software Engineers to deliver state-of-the-art performance for an LLM serving stack. You will optimize GPU kernels, compilers, runtimes, and distributed inference systems to improve latency, throughput, reliability, and hardware efficiency. Successful candidates combine strong systems engineering, deep performance expertise, disciplined measurement, and effective cross-team collaboration. As a Senior Software Engineer, you will own significant performance improvements across GPU kernels and inference runtime components, carrying optimizations from investigation through production. As a Principal Software Engineer, you will tackle the most difficult cross-stack performance challenges and create reusable capabilities that advance serving performance across models and hardware generations. At Microsoft, our mission to empower every person and every organization on the planet to achieve more guides how we partner with customers to deliver trusted, impactful solutions. With a growth mindset culture, we innovate responsibly and measure success by shared progress people, teams, and customers. Join us to do meaningful work that changes the world and helps shape what’s next for everyone.

Requirements

Bachelor’s Degree in Computer Science or a related technical field and 4+ years of technical engineering experience coding in languages such as C++, 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.
Expertise in GPU or equivalent accelerator programming and kernel optimization.
Familiarity with vLLM, SGLang, or equivalent LLM inference libraries.
Demonstrated cross-team collaboration and technical ownership.
Ability to use AI-assisted development tools efficiently and validate their output.
Deep expertise in GPU or equivalent accelerator compilation pipelines and low-level architecture.
Expertise in LLM training and inference parallelism and acceleration.
Demonstrated ownership of cross-team technical initiatives from strategy through production.
Track record of creating reusable platforms, influencing senior stakeholders, and mentoring technical leaders.

Responsibilities

Develop and optimize GPU kernels and runtime components for state-of-the-art LLM serving performance.
Profile workloads and improve latency, throughput, and hardware efficiency.
Integrate robust, maintainable optimizations into production serving systems.
Collaborate across model, compiler, infrastructure, and hardware teams.
Use AI-assisted development tools effectively to accelerate the development process.
Contribute to technical reviews, engineering standards, and mentoring.
Embody Microsoft’s culture and values.
Drive cross-stack optimization across kernels, compilers, runtimes, and distributed serving.
Perform difficult, low-level optimization and resolve critical performance bottlenecks.
Turn performance innovations into reusable production capabilities.
Collaborate across research, infrastructure, and hardware teams to deliver measurable improvements.
Mentor senior engineers and raise engineering standards.