Lead Software System Design Eng - System PNP
AMD · Bengaluru · 14+ yrs experience · Posted 2026-05-26
Tech stack: C, C++, Linux, Python
Apply on the company site · Get a referral for this role
AMD salary & ratings · AMD interview process · More live openings
About the role
Lead Software System Design Eng - System PNP Role Overview We are seeking a highly motivated System Power & Performance Engineer to join our System PnP team. This role will have a dual focus: Benchmarking, Profiling, and bottleneck analysis on AMD’s system PnP stack, with emphasis on Linux and virtualized environments.
Responsibilities:
- System Power & Performance / PnP
- Plan, execute and own system performance including low level profiling and bottleneck analysis on AMD’s SoCs, focusing on Linux (Ubuntu, Yocto) and virtualized software stacks for Robotics, automotive and industrial.
- Perform benchmark characterization, system-level tuning, micro architecture and workload analysis across CPU, GPU, NPU, AI and memory subsystems.
- Collaborate with SoC architects, BIOS/FW teams, and software developers to identify performance gaps and recommend optimizations.
- Generate comprehensive technical reports, dashboards, and documentation for leadership reviews, customer engagements, and outbound collateral.
- Contribute to automation for benchmark execution, data collection, and results visualization.
- Work with cross-functional teams to debug system-level issues blocking performance goals.
- Competitive Benchmarking
- Drive competitive benchmarking initiatives by running workloads on competitive platforms (Nvidia, Intel, Qualcomm, ARM-based SoCs) and building comparative landscapes across segments (client, embedded, industrial, automotive).
- Build comparative performance landscapes across segments including client, embedded, server, industrial, and automotive.
- Provide actionable insights that help influence future SoC, firmware, and platform design.
- Automation, Reporting & Documentation
- Support development of automation for benchmark execution, data collection, and results visualization.
- Generate technical reports, dashboards, and documentation for leadership and customer engagements.
- Foster continuous improvement and innovation within validation and performance analysis environments.
- Required Skills & Experience
- 14+ years of relevant experience in system performance engineering, profiling, bottleneck analysis, or post-silicon validation.
- Perception pipelines (SLAM, visual‑odometry, sensor fusion)
- Planning & control loops
- Kinematics, dynamics, and real-time constraints
- Middleware communication patterns: pipes, shared memory, zero‑copy
- Expert in Linux internals (scheduling, memory management), Real Time systems (RT kernel, interrupt and jitter), QoS Tuning.
- Hands on in performance profiling tools: Perf, valgrind, LTTng, perfetto, Trace Compass, wireshark, Nsight, Vtune, Oprofile, Flameghraphs, GPU Perf studio etc
- Proficiency in Python/Bash/C/C++/Perl for automation, data processing, and reporting.
- Proven cross-team collaboration skills and ability to drive complex debug efforts.
Qualifications:
- Experience with virtualization technologies (Xen, KVM, Hyper-V, container environments).
- Exposure to post-silicon bring-up, system validation flows, and early silicon testing.
- Experience with competitive benchmarking methodologies and customer-facing documentation.
- Debug expertise at system level and SoC level.
- Bachelor’s or Master’s degree in Computer Engineering, Electrical Engineering, Computer Science, or a related field.
Qualifications
- Experience with virtualization technologies (Xen, KVM, Hyper-V, container environments).
- Exposure to post-silicon bring-up, system validation flows, and early silicon testing.
- Experience with competitive benchmarking methodologies and customer-facing documentation.
- Debug expertise at system level and SoC level.
- Bachelor’s or Master’s degree in Computer Engineering, Electrical Engineering, Computer Science, or a related field.
Responsibilities
- System Power & Performance / PnP
- Plan, execute and own system performance including low level profiling and bottleneck analysis on AMD’s SoCs, focusing on Linux (Ubuntu, Yocto) and virtualized software stacks for Robotics, automotive and industrial.
- Perform benchmark characterization, system-level tuning, micro architecture and workload analysis across CPU, GPU, NPU, AI and memory subsystems.
- Collaborate with SoC architects, BIOS/FW teams, and software developers to identify performance gaps and recommend optimizations.
- Generate comprehensive technical reports, dashboards, and documentation for leadership reviews, customer engagements, and outbound collateral.
- Contribute to automation for benchmark execution, data collection, and results visualization.
- Work with cross-functional teams to debug system-level issues blocking performance goals.
- Competitive Benchmarking Drive competitive benchmarking initiatives by running workloads on competitive platforms (Nvidia, Intel, Qualcomm, ARM-based SoCs) and building comparative landscapes across segments (client, embedded, industrial, automotive).
- Build comparative performance landscapes across segments including client, embedded, server, industrial, and automotive.
- Provide actionable insights that help influence future SoC, firmware, and platform design.
- Automation, Reporting & Documentation
- Support development of automation for benchmark execution, data collection, and results visualization.
- Generate technical reports, dashboards, and documentation for leadership and customer engagements.
- Foster continuous improvement and innovation within validation and performance analysis environments.
- Required Skills & Experience
- 14+ years of relevant experience in system performance engineering, profiling, bottleneck analysis, or post-silicon validation.
- Perception pipelines (SLAM, visual‑odometry, sensor fusion)
- Planning & control loops
- Kinematics, dynamics, and real-time constraints
- Middleware communication patterns: pipes, shared memory, zero‑copy
- Expert in Linux internals (scheduling, memory management), Real Time systems (RT kernel, interrupt and jitter), QoS Tuning.
- Hands on in performance profiling tools: Perf, valgrind, LTTng, perfetto, Trace Compass, wireshark, Nsight, Vtune, Oprofile, Flameghraphs, GPU Perf studio etc
- Proficiency in Python/Bash/C/C++/Perl for automation, data processing, and reporting.
- Proven cross-team collaboration skills and ability to drive complex debug efforts.