1 day ago
Bengaluru, IndiaSenior
Responsibilities
- Identify and characterize critical ML workloads and models for CPU-centric execution, including compute intensity, memory behavior, parallelism, and dataflow.
- Generate execution traces with QEMU or equivalent simulators and develop tooling to capture instruction behavior, performance counters, and bottlenecks.
- Analyze CPU pipelines, memory hierarchy, and instruction utilization, then optimize hotspots through kernel tuning, algorithmic improvements, and data-layout optimization.
- Collaborate with CPU architecture and design teams to provide workload insights and propose enhancements to compute units, SIMD extensions, and memory subsystems.
- Develop optimized ML kernels and libraries for QMX, including GEMM, convolution, attention, and activation functions.
- Integrate optimized kernels with ML frameworks and inference stacks and apply vectorization, cache-aware execution, and parallel execution strategies.
- Benchmark and optimize CPU-centric ML workloads, establish performance baselines, track improvements, and perform competitive performance analysis.
Requirements
- Bachelor’s degree in Engineering, Information Systems, Computer Science, or a related field plus 8+ years of related experience; alternatively, a master’s degree plus 7+ years or a PhD plus 6+ years.
- 4+ years of work experience with programming languages such as C, C++, Java, or Python.
- Strong background in computer architecture, systems programming, and machine learning fundamentals.
- Mandatory proficiency in C/C++ and experience with performance profiling, benchmarking, and optimization.
- Preferred experience with QEMU or equivalent simulators and ML kernel development for GEMM, convolution, or attention.
- Knowledge of CPU pipelines, caching, SIMD/vector extensions such as NEON, SVE, and QMX.
- Familiarity with ML frameworks and inference stacks, plus low-level optimization using intrinsics, assembly, and memory/cache tuning.
Benefits
- Work on next-generation QMX CPU architectures and influence hardware design through real workload insights.
- Solve end-to-end ML performance challenges from models and kernels through silicon while collaborating with architecture, systems, and AI teams.
- Role location is Bangalore or relevant location; the posting lists Engineer, Senior Engineer, Staff Engineer, and Principal Engineer levels.
About Qualcomm
Qualcomm is a public semiconductor company headquartered in San Diego, founded in 1985, that designs and sells wireless chipsets and platforms for mobile devices, automotive, IoT, and networking, notably the Snapdragon application processors and 5G modems. It also licenses a large portfolio of cellular patents to device makers, generating revenue alongside chip sales; its technology underpins many Android smartphones and emerging automotive and edge-compute systems, and it trades on NASDAQ as QCOM.