Lead Engineer, Senior-System Performance Engineer (NSP, AI/ML, CPU, DDR)

Overview

Join the System Performance team responsible for profiling and optimizing system performance on Snapdragon Data center chipsets, with a focus on AI/ML performance using NPU cores.

What you'll do

• Drive performance analysis on silicon using System and Core benchmarks such as Dhrystone, GeekBench, SPECInt, and CNN/GenAI ML networks.
• Use performance tools to analyze load patterns across IPs and identify performance bottlenecks in the system.
• Analyze performance KPIs of SoC subsystems such as NPU, CPU and memory, and correlate performance with projections.
• Evaluate and characterize performance at various junction temperatures and optimize operation at high ambient temperatures.
• Analyze and optimize system performance parameters of SoC infrastructure such as NoC and LP5 DDR.
• Collaborate with cross-functional global teams to plan and execute performance activities on chipsets and make recommendations for next-generation chipsets.

What you'll need

• Deep understanding of NPU, CPU and DDR architecture internals.
• Understanding of NPU micro-architecture, including specialized processing elements for matrix multiplications and convolutions.
• Strong grasp of deep learning fundamentals, including CNNs, transformers and GenAI.
• Understanding of the distinction between compute-intensive model training (often on GPUs) and inference on NPUs.
• Knowledge of model optimization and compression techniques such as quantization, pruning and distillation.
• Understanding of CPU caches (L1, L2, L3), instruction pipelines, branch prediction, memory hierarchy and multi-core/multi-threaded processing.
• Understanding of how memory access, instruction dependencies and contention for shared resources impact performance.
• Understanding of JEDEC LPDDR4, LPDDR5 and LPDDR6 specifications, including command and timing parameters (e.g., tCL, tRCD, tRP), memory organization, and training and initialization sequences.
• Understanding of how a memory controller works and its features such as command queue, port arbitration and control schemes.
• Familiarity with frameworks such as TensorFlow Lite, PyTorch Mobile and ONNX Runtime for preparing models for deployment.
• Experience with NPU-specific compilers such as Qualcomm QNN, Arm Vela and Intel OpenVINO to optimize and orchestrate AI workloads.
• Ability to evaluate hardware and software for AI tasks and measure metrics such as TOPS/W.
• Experience using the Windows Performance Toolkit and Qualcomm's Snapdragon Profiler to analyze NPU and system-level performance.
• Core understanding of parallel processing architectures for efficient AI computation.
• Expertise in how operating systems manage processes, threads, memory, MMU and interrupt handling, including kernel scheduler and system-level bottlenecks.
• Good understanding of CPU benchmarks (such as GeekBench, SpecInt and CoreMark) and DDR benchmarks (such as lat_mem, stream and bw_mem) and how they exercise CPU, GPU and DDR architecture.
• Experience with performance monitoring tools such as Intel VTune, Linux perf, and utilities like top, vmstat, iostat and netstat.
• Experience with software tools to monitor system hotspots, command bus utilization and memory traffic patterns, including validating software-generated traffic.
• Good understanding of memory allocation policies, prefetching and caching to minimize latency and maximize bandwidth.
• Skill in profiling code to analyze memory access patterns and optimize for data locality.
• Strong statistical skills for analyzing large performance datasets, such as histograms of transaction latencies and derived performance metrics.
• 5+ years of industry experience working on ARM/x86 based platforms, mobile/automotive/data center operating systems and/or performance profiling tools.
• Experience in application or driver development in Linux or QNX; ability to create and customize makefiles with various compiler options.
• Ability to learn quickly and adapt to new technologies.
• Excellent communication skills.
• Bachelor's degree in Engineering, Information Systems, Computer Science or related field and 3+ years of Systems Engineering or related work experience; OR Master's degree in a related field and 2+ years of Systems Engineering or related work experience; OR PhD in a related field and 1+ year of Systems Engineering or related work experience.
• Required education: Bachelor's in Computer Engineering and/or Electrical Engineering.

Nice to have

• Knowledge of computer architecture, LP5 DDR and bus/NoC profiling.
• Fundamentals of an operating system such as Linux, QNX or a hypervisor, and experience with data center applications.
• Experience creating professional reports and slides using MS Office or advanced visualization tools.
• Experience in PoC development and competitive analysis.
• Knowledge of voltage, power and thermal domains.
• Preferred education: Master's in Computer Engineering and/or Electrical Engineering.

Details

• Location: Bangalore, India.