Senior AI Memory Architect

Hp Iq; Houston (TX); Presencial; USD 170 000 - 230 000; Tempo integral

Vantagens oferecidas por esta oferta de emprego

Health insurance

Vision insurance

Disability insurance

Employee assistance program

Flexible spending account

Life insurance

Parental leave

Holidays

Resumo da oferta

HP's Memory Management organization is building an AI memory platform to optimize memory use across AI workloads on client devices and cloud. The Senior Software Engineer will define architecture for memory management, enabling efficient model deployment on CPUs, GPUs, NPUs, and managing QoS, residency, and KV caches while coordinating with silicon partners and AI frameworks.

The role requires deep OS/memory architecture expertise, cross-functional leadership, and a track record delivering

Qualificações

• Four-year or graduate degree in CS/CE/SE or equivalent experience.
• 12+ years of industry experience in OS, systems software, AI infra, memory management, or performance engineering.
• Proven track record delivering scalable platform technologies, runtime systems, or enterprise software architectures.
• Experience building software that operates close to hardware and operating system layers.

Responsabilidades

• Define end-to-end architecture for HP's Memory Management platform.
• Architect memory allocation, prioritization, and optimization across AI workloads.
• Lead design of model residency management to enable efficient deployment/execution of large AI models on resource-constrained systems.
• Define policies for KV cache management, context window optimization, model sharing, and memory multiplexing across multiple AI agents.
• Develop policy engines that balance performance, memory consumption, power usage, and user responsiveness.
• Architect workload QoS and resource arbitration across CPU, GPU, NPU, memory, storage, and network resources.
• Define strategies for local, hybrid, and cloud model execution based on state and resources.
• Lead telemetry/analytics systems to monitor memory pressure, model utilization, and resource contention.
• Collaborate with OS, firmware, silicon, and AI framework teams to optimize memory behavior across the stack.
• Establish roadmaps, engineering standards, and architectural guidance across software teams.
• Mentor senior engineers and architects; influence AI platform strategy.

Conhecimentos

C++

Python

Systems programming

Leadership

Windows internals

Formação académica

Four-year or graduate degree in CS/CE/SE

Ferramentas

ONNX Runtime

OpenVINO

DirectML

TensorRT

CUDA

ROCm

Qualcomm AI SDKs

Descrição da oferta de emprego

HP's Memory Management organization is building an AI memory platform to optimize memory use across AI workloads on client devices and cloud. The Senior Software Engineer will define architecture for memory management, enabling efficient model deployment on CPUs, GPUs, NPUs, and managing QoS, residency, and KV caches while coordinating with silicon partners and AI frameworks.

The role requires deep OS/memory architecture expertise, cross-functional leadership, and a track record delivering