Senior Principal Software Engineer, Core Infrastructure

Oracle•Nashville, TN

About The Position

Oracle Cloud Infrastructure is seeking a Senior Principal Software Engineer to build a new Data Processing Unit (DPU) platform spanning networking and storage. The role addresses system-level challenges including host-versus-DPU responsibilities, predictable tail latency under mixed workloads, and correct behavior across offload transitions, failures, and upgrades. The engineer will own a major subsystem spanning components and teams. Depending on the assignment, this may involve a storage I/O pipeline, packet processing pipeline, host-to-DPU data path, or infrastructure acceleration subsystem. The role defines architectural boundaries, aligns component owners, and remains accountable for integration and subsystem outcomes. Candidates may bring deep expertise in storage data paths with working familiarity in networking, or deep networking data path expertise with working familiarity in storage. Primary ownership will draw on the engineer’s strengths while requiring collaboration across both domains. The position combines architectural ownership and cross-team technical leadership with hands-on implementation and debugging. It includes establishing performance expectations, leading subsystem qualification and production readiness, and mentoring component owners. The engineer will also guide effective AI use in subsystem engineering, with validation and clear accountability.

Requirements

10 or more years of professional software engineering experience in systems or infrastructure software, including substantial hands-on experience building high-performance storage data paths or networking data paths.
Demonstrated technical ownership of a major subsystem spanning multiple components and engineering teams, from ambiguous requirements through production integration.
Deep expertise in storage data path architecture, implementation, and optimization, or networking data path architecture, implementation, and optimization.
Strong hands-on C or C++ expertise and deep knowledge of Linux, synchronization, memory management, multicore architectures, and performance analysis.
Working familiarity with the complementary domain: networking fundamentals and transport behavior for storage specialists, or storage I/O architecture and behavior for networking specialists.
Ability to evaluate cross-domain performance and failure interactions with partner engineers.
Experience defining component boundaries and contracts, establishing performance budgets, and resolving cross-component correctness and reliability issues.
Record of driving technical alignment and delivery across teams while remaining actively involved in implementation and difficult debugging.
Ability to explain complex architectural decisions and develop other engineers into effective component owners.
Bachelor’s degree in Computer Science, Computer Engineering, or a related discipline, or equivalent practical experience.

Nice To Haves

Experience with DPU architecture, including DPUs, SmartNICs, AMD Pensando, NVIDIA BlueField/DOCA, P4, or comparable technologies, and software, firmware, and hardware interface design.
Architecture or substantial extension of DPDK-based systems or comparable user-space packet processing frameworks.
Storage I/O pipeline design or optimization, block storage, NVMe, NVMe over Fabrics, RDMA, or storage virtualization experience.
Hardware co-design, PCIe, DMA, SR-IOV, IOMMU, zero-copy techniques, fleet qualification, failure recovery, or upgrade compatibility experience.

Responsibilities

Own subsystem architecture and outcomes by turning ambiguous system requirements into an architecture, component contracts, and a phased delivery plan.
Establish decision authority and resolve tradeoffs that individual component owners cannot settle independently.
Evaluate partitioning across host, DPU software, firmware, and hardware; validate decisions about queueing, memory ownership, acceleration, and recovery using prototypes and representative workloads.
Decompose subsystem work, align technical dependencies, and resolve integration risks across teams.
Guide implementation through other engineers while personally implementing or debugging critical paths.
Establish subsystem performance budgets and targets for throughput, tail latency, resource efficiency, and relevant storage I/O or packet processing metrics.
Resolve bottlenecks spanning component boundaries.
Work across storage and networking to evaluate I/O processing, transport, ordering, buffering, backpressure, and recovery tradeoffs.
Ensure local optimizations preserve end-to-end performance, availability, and data integrity.
Lead subsystem qualification and technical readiness reviews.
Establish compatible interfaces, observability, fault isolation, and safe upgrade behavior; resolve systemic risks during rollout and operation.
Mentor engineers in architectural judgment and systems debugging, establish shared engineering practices, and help component leaders make sound decisions independently.
Guide effective AI use across subsystem engineering work, emphasizing validation and clear accountability, and share approaches that improve quality and productivity, reduce repetitive debugging and documentation, and support employee well-being.