1 day ago
Bengaluru, IndiaSenior
Responsibilities
- Design and develop scalable stress, performance, validation, and benchmarking frameworks for MAIA AI accelerator platforms.
- Build synthetic and production-inspired AI workloads, including training, inference, GEMM, attention, collective communication, and memory-intensive workloads.
- Develop and optimize kernels for custom AI accelerators using Python, C++, PyTorch, Triton, and MAIA SDKs.
- Integrate tooling with MAIA compiler pipelines, SDKs, runtime environments, and performance analysis systems.
- Automate workload deployment, orchestration, telemetry collection, model compilation, kernel validation, regression testing, and result analysis.
- Create validation suites for silicon bring-up, qualification, reliability, correctness, performance, thermal, power, and stability testing.
- Characterize system performance across compute, networking, memory, and storage subsystems and drive root-cause analysis.
- Build developer productivity, diagnostics, debugging, dashboards, failure-triage, and reporting infrastructure.
Requirements
- Bachelor’s or master’s degree in Computer Science, Computer Engineering, Electrical Engineering, or equivalent experience.
- 8+ years of software development experience.
- Strong programming skills in Python and C/C++.
- Experience designing production-quality software systems and frameworks.
- Experience developing workloads for GPUs, AI accelerators, or HPC systems and understanding AI training and inference workloads.
- Hands-on experience with PyTorch, Triton, distributed AI workloads, and compute-intensive kernel optimization.
- Understanding of accelerator architectures, compute engines, memory hierarchies, interconnects, and runtime systems.
- Experience with performance profiling, bottleneck analysis, workload optimization, stress or benchmark workloads, automated test frameworks, and regression infrastructure.
- Strong debugging and root-cause analysis skills across hardware and software boundaries.
- Preferred experience with custom AI accelerator SDKs, compiler ecosystems, LLVM, MLIR, Triton Compiler, kernel generation, LLM training and inference, collective communication, networking, large-scale AI clusters, CI/CD systems, containerized environments, cloud-scale validation, or silicon bring-up and post-silicon validation.
- Ability to meet Microsoft, customer, and/or government security screening requirements, including the Microsoft Cloud Background Check.
About Microsoft
Microsoft develops operating systems, productivity software, cloud services, developer tools, and consumer devices for individuals, enterprises, and governments. Its main products include Windows, Microsoft 365, Azure, Visual Studio/GitHub, Xbox, and LinkedIn; revenue comes from software subscriptions and licenses, cloud consumption, hardware sales, and advertising. Founded in 1975 and headquartered in Redmond, Washington, Microsoft is a public company traded on Nasdaq.