Senior System Software Engineer - Datacenter Power Management

Description

The company builds accelerated computing platforms for data centers, combining GPUs, CPUs, networking, systems and software. This senior system software engineer role sits on the datacenter performance and power management software team.

The work spans hardware design, embedded firmware, drivers, operating systems and AI workloads, from early architecture and pre-silicon validation through silicon bring-up, productization and rollout in large data-center fleets.

Responsibilities

• Design, build and debug production software for data-center power management controllers, with a focus on end-to-end power control at rack and data hall level.
• Extend cluster-level dynamic provisioning and power control systems for next-generation data centers.
• Write real-time controllers and policies that tune performance, power, thermals and energy efficiency under heavy data-center load.
• Own features from requirements through architecture, coding, pre-silicon validation, silicon bring-up, productization and production support.
• Work with GPU architects and hardware designers to define hardware-software interfaces and shape power features in future processors.
• Study how workloads, clocks, voltages, power limits, thermals, telemetry and system policies interact.
• Lead root-cause work on power, performance, stability and reliability problems across firmware, drivers, hardware and platform software.
• Create validation plans and automation covering functional correctness, transition latency, performance per watt and robustness across operating conditions.
• Write architecture, interface and specification documents for new power-management features.
• Coordinate with architecture, ASIC, firmware, driver, validation, platform and data-center systems teams spread across locations.

Requirements

• BS or MS in computer science, computer engineering, electrical engineering or a related field, or equivalent experience.
• 12+ years of substantial industry experience building system software, embedded firmware, device drivers or other hardware-related production code.
• Strong C skills, including building, debugging and maintaining complex low-level code.
• Solid grasp of OS fundamentals, driver architecture, embedded or real-time software, concurrency, interrupt handling and hardware programming.
• Ability to read hardware specifications and build software interfaces for registers, telemetry, interrupts and control mechanisms.
• Strong grasp of computer architecture and how hardware and software interact.
• Proven record of independently debugging hard problems across several software and hardware layers.
• Clear written and verbal communication, and a history of working well across organizational and geographic boundaries.
• Ways to stand out: experience architecting, designing or implementing datacenter provisioning, monitoring and power management at a CSP or NCP.
• Ways to stand out: hands-on work with power and performance management on GPUs, CPUs, accelerators or SoCs.
• Ways to stand out: background in P-state selection, DVFS, clock or voltage control, power capping, thermal management, throttling or workload-aware control policies.
• Ways to stand out: experience with real-time feedback controllers, including stability, responsiveness, hysteresis, latency and noisy telemetry.
• Ways to stand out: understanding of voltage-frequency relationships, transient power, thermal limits, power delivery and system power budgets.

Conditions

Base salary depends on location, experience and pay for similar roles. The range is 224,000 USD to 356,500 USD for Level 5, and 272,000 USD to 431,250 USD for Level 6.

Applications are accepted at least until October 27, 2026.

This posting is for an existing open position.

The company uses AI tools in its recruiting processes.

The company is an equal opportunity employer and does not discriminate on any protected characteristic, including in hiring and promotion.