CPU Software & Hardware Co-Design Engineer (ML Systems)
Technology, Data & Digital · Software & Web Development · Software Engineering · Machine Learning
In short
Qualcomm is seeking a CPU Software & Hardware Co-Design Engineer specializing in ML Systems. This role involves co-designing next-generation QMX architectures, optimizing ML workloads from models to kernels, and providing architectural feedback. Responsibilities include workload characterization, simulation, bottleneck analysis, and developing optimized ML kernels and libraries.
Responsibilities
- Identify and prioritize critical ML use cases and models for CPU-centric execution.
- Analyze workload characteristics including compute intensity, memory bandwidth, cache behavior, and parallelism.
- Generate detailed execution traces for ML workloads using QEMU or equivalent simulators.
- Develop tooling to capture instruction-level execution behavior and extract performance counters.
- Identify system bottlenecks across CPU pipelines, memory hierarchy, and instruction utilization.
- Optimize critical hotspots through kernel-level tuning, algorithmic improvements, and data layout optimizations.
- Collaborate with CPU architecture and design teams to provide data-driven insights and propose architectural enhancements.
- Influence next-generation CPU features in compute units, vector/SIMD extensions (e.g., QMX), and memory subsystems.
- Design and implement highly optimized ML kernels and libraries for QMX architecture.
- Enable integration with open-source ML frameworks (e.g., PyTorch, ONNX, XNNPACK, MLAS).
- Apply advanced optimizations like SIMD/vectorization, cache-aware execution, and parallel execution strategies.
- Optimize CPU-centric ML benchmarks and establish performance baselines.
- Perform competitive analysis and performance positioning.
Requirements
- Strong background in Computer Architecture / Systems Programming and Machine Learning fundamentals.
- Proficiency in C/C++ (mandatory).
- Experience with Performance profiling, benchmarking, and optimization.
Desired Qualifications
- Experience with QEMU or equivalent simulators.
- Experience with ML kernel development (GEMM, convolution, attention).
- Knowledge of CPU architecture (pipelines, caching, SIMD/vector extensions such as NEON, SVE, QMX).
- Familiarity with ML frameworks and inference stacks.
- Experience with low-level optimization: intrinsics, assembly, memory and cache tuning.
Benefits
- Competitive annual discretionary bonus program.
- Opportunity for annual RSU grants.
- Highly competitive benefits package designed to support success at work, at home, and at play.
Skills
C++Machine LearningComputer ArchitectureSystems ProgrammingPerformance ProfilingBenchmarkingOptimizationQEMUGEMMConvolutionAttentionPyTorchONNXXNNPACKMLASSIMDNEONSVEQMX
#CPU#Software#Hardware#Co-Design#ML#Systems#Engineering#Architecture#Machine Learning#Performance Optimization#Embedded#Cloud Edge
About Qualcomm
Enabling a world where everyone and everything can be intelligently connected.
Enabling a world where everyone and everything can be intelligently connected.\n\n
Company
QualcommJob Posted
1 week ago
Employment Type
Full Time
Work mode
Remote
Salary
US$177,300–265,900 · Negotiable
Experience Level
Senior
Locations
United States of America
Qualification
Bachelor, Master, Doctoral
Applicants
Be an early applicant
Similar Jobs
IKEA
Bangkok, ThailandPart Time Recovery Assistant (Sales at As-Is Area), IKEA Sukhumvit
Part Time Be an early applicant Posted 4 days ago
Accenture
Bangalore, India +3 moreAGBG Mid Market Offshore Delivery Lead
Full Time Be an early applicant Posted 3 days ago
Accenture
Hyderabad, India +6 moreAnalyst- Program Management
Full Time Be an early applicant Posted 3 days ago
Accenture
Hyderabad, India +6 moreAnalyst - Program Management
Full Time Be an early applicant Posted 3 days ago
HCLTech
Noida, IndiaTest Lead - Performance Testing, Jmeter, LoadRunner
Full Time Be an early applicant Posted 3 days ago
HCLTech
Hyderabad, IndiaSAP ABAP Senior Technical Lead
Full Time Be an early applicant Posted 3 days ago