Senior System Software Engineer – GPU Power Management

This is a fully remote position, open to applicants in California, +2 more states.

📋 Description

• Design, develop, implement, and troubleshoot GPU power and performance management software, particularly focusing on P-state management and Dynamic Voltage and Frequency Scaling (DVFS).

• Create real-time controllers, policies, and mechanisms that dynamically enhance GPU performance, power efficiency, thermal management, and energy conservation under challenging data center workloads.

• Lead features throughout the entire product lifecycle: requirements gathering, architecture, implementation, pre-silicon validation, silicon bring-up, productization, and ongoing production support.

• Work closely with GPU architects and hardware designers to establish hardware-software interfaces and impact the power management capabilities of future processors.

• Examine intricate interactions between workloads, clocks, voltages, power constraints, thermal conditions, telemetry, and system-level policies.

• Spearhead the analysis and resolution of intricate power, performance, stability, and reliability challenges across firmware, drivers, hardware, and platform software.

• Formulate validation strategies and automation processes to ensure functional correctness, transition latency, performance-per-watt, and robustness in various operating conditions.

• Develop comprehensive architecture, interface, and specifications for new power management features.

• Collaborate with globally distributed teams in architecture, ASIC design, firmware development, driver creation, validation, platform management, and data center systems.

⛳️ Requirements

• A BS or MS degree in Computer Science, Computer Engineering, Electrical Engineering, or a related discipline—or equivalent experience.

• Over 12 years of substantial industry experience in system software development, embedded firmware, device drivers, or other production software related to hardware.

• Proficient programming skills in C, with experience in developing, debugging, and maintaining intricate low-level software.

• In-depth knowledge of operating system principles, device driver architecture, embedded or real-time software, concurrency, interrupt handling, and hardware programming.

• Experience in interpreting hardware specifications and creating software interfaces for registers, telemetry, interrupts, and control mechanisms.

• Strong grasp of computer architecture and hardware-software interactions.

• Demonstrated ability to independently troubleshoot complex issues across various software and hardware layers.

• Exceptional written and verbal communication skills, with a proven history of effective collaboration across organizational and geographical boundaries.

• Practical experience with GPU, CPU, accelerator, or SoC power and performance management.

• Familiarity with developing or implementing P-state selection, DVFS, clock control, voltage control, power capping, thermal management, throttling, or workload-aware control policies.

• Experience in developing real-time feedback controllers, including considerations of stability, responsiveness, hysteresis, latency, and noisy telemetry.

• Awareness of electrical and platform aspects such as voltage-frequency relationships, transient power, thermal limits, power delivery, and system-level power budgets.

🏝️ Benefits

• Equity

• Benefits