Software Engineer - On-Device & Backend Systems

Meta•Redmond, WA

11d•$183,997 - $257,000•Onsite

About The Position

Meta is building the next generation of intelligent devices powered by custom silicon and deeply integrated cloud services. As a Staff Software Engineer on this team, you will own the end-to-end software architecture that spans Meta's custom SoC platform, on-device AOSP-based software, and the backend services that extend device capabilities into the cloud. You will drive the most complex cross-boundary technical decisions—bridging low-level hardware abstraction, Android platform software, and scalable backend infrastructure—to deliver seamless, high-performance experiences. This role demands deep expertise across embedded/on-device systems and distributed backend services, and the ability to lead major initiatives that require tight coordination between silicon, device software, and cloud teams.

Requirements

Bachelor's degree in Computer Science, Computer Engineering, relevant technical field, or equivalent practical experience
10+ years of experience in systems software engineering, with significant depth in both on-device/embedded platforms and backend/distributed systems
Experience leading complex initiatives that span hardware–software–cloud boundaries with demonstrated org-level impact
Deep understanding of Android platform internals (AOSP): system services, HAL interfaces, native frameworks, and build/integration workflows
Strong proficiency in C/C++ for on-device systems programming and Java/Kotlin or Python/C++ for backend service development
Experience working with custom silicon or SoC platforms—including hardware bring-up, driver integration, or hardware abstraction layer development
Experience designing and operating large-scale backend services (e.g., RPC frameworks, data pipelines, model serving, distributed storage)
Track record of solving highly complex technical problems that span multiple systems, teams, and organizational boundaries
Experience with system-level debugging across the full stack: hardware traces, OS-level profiling, network diagnostics, and backend service observability
Experience shipping consumer devices or embedded systems at scale alongside their supporting cloud infrastructure

Nice To Haves

Experience with large-scale backend infrastructure (RPC frameworks, distributed data stores, real-time analytics) or equivalent service frameworks
Familiarity with custom silicon workflows: firmware/software co-design, DSP programming, hardware accelerator integration, or silicon validation
Experience with on-device ML inference, model optimization (quantization, compilation for custom accelerators), and cloud-to-device model deployment pipelines
Proficiency in power-aware software design: balancing on-device compute vs. cloud offload for battery life, thermal, and latency constraints
Experience with OTA systems, device fleet management, or A/B experimentation frameworks for hardware products
Background in real-time or low-latency systems: sensor fusion, streaming media, or interactive workloads that span device and cloud
Experience with wearable devices, AR/VR systems, mobile platforms, or IoT at scale
Track record of leading large-scale projects from silicon bring-up through mass production and live service operation
Experience adhering to and implementing responsible, ethical AI practices (e.g., risk assessment, bias mitigation, quality and accuracy reviews)
Demonstrated ability to integrate AI tools to optimize engineering workflows and drive measurable efficiency gains
Experience defining APIs and contracts between on-device and backend systems that remain stable across hardware generations

Responsibilities

Define and drive the end-to-end system architecture spanning on-device software (AOSP, Meta custom SoC interfaces) and Meta's backend services, ensuring coherent data flow, low latency, and reliability across the full stack
Lead the design and implementation of platform software that leverages Meta's custom SoC capabilities—including hardware accelerators, DSPs, and specialized compute units—through AOSP system services, HALs, and native frameworks
Own resolution of the most complex, ambiguous technical problems that cross the device–cloud boundary: diagnosing issues that manifest across silicon bring-up, OS layers, network transport, and backend service interactions
Architect backend services that support on-device workloads—including model serving, telemetry pipelines, OTA update infrastructure, device management, and cloud offload—optimizing for scale, availability, and cost efficiency
Drive performance optimization across the full stack: silicon-aware scheduling on-device, efficient serialization and transport protocols, and backend service latency/throughput at scale
Partner with silicon/hardware teams to define software requirements for Meta's custom SoC, influence silicon roadmaps, and ensure platform software fully exploits custom hardware capabilities
Establish system-level metrics, monitoring, and reliability frameworks that provide end-to-end observability from on-device health through backend service SLAs
Collaborate cross-functionally with silicon, firmware, OS platform, product, ML/AI, and infrastructure teams to align technical strategies, unblock dependencies, and drive org-level outcomes
Communicate architecture decisions, integration strategies, and technical trade-offs to stakeholders at all levels—driving alignment across device and backend organizations
Leverage AI tools and workflows to accelerate development, improve system analysis, and scale your impact across the organization