LLM
About HP
At HP, you’ll have a chance to create tools, technology, and solutions that reshape the way the world works in the future. If you’re looking to join a company that allows you to connect with a network of professionals eager to support you in doing your best work, we want to talk to you. Our legendary culture guides every employee toward success—fostering collaboration and driving innovation.
Operating in over 170 countries, HP is always creating new services, products, and capabilities giving you more opportunities to advance your career. Here, innovation is the key to professional development and career mobility.
When you join HP, you’re joining a company that believes every voice matters and that we all deserve a seat at the table. From the boardroom to factory floor, we create a culture where everyone is respected and where people can be themselves. You will be part of a global laboratory where different perspectives and experiences will help you solve problems in new ways. This is where you can build a long and wide-ranging career.
Job Summary
The Commercial Systems Software Engineering organization is developing HP's Memory Management platform, a foundational component of the Agentic AI Software Stack designed to optimize memory utilization, model execution, and resource orchestration for next-generation AI PCs.
The Senior Software Engineer will define the architecture and technical strategy for AI memory management across heterogeneous compute environments, including CPUs, GPUs, NPUs, storage, and cloud resources. The role will focus on enabling efficient execution of large language models, multi-agent workloads, multimodal AI applications, and enterprise AI scenarios through intelligent memory allocation, model residency management, KV cache optimization, workload prioritization, and Quality of Service (QoS) controls.
This position requires deep expertise in operating systems, memory architectures, AI runtime systems, workload scheduling, performance optimization, and large-scale software architecture. The architect will work closely with silicon vendors, operating system partners, AI framework teams, and product organizations to develop innovative technologies that maximize AI performance while maintaining system responsiveness, security, and power efficiency.
Responsibilities
•
Define and drive the end-to-end architecture for HP's Memory Management platform.
•
Architect systems for intelligent memory allocation, prioritization, and optimization across AI workloads running on client devices.
•
Lead design of model residency management capabilities to enable efficient deployment and 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 dynamically balance performance, memory consumption, power usage, and user responsiveness.
•
Architect workload QoS and resource arbitration mechanisms across CPU, GPU, NPU, memory, storage, and network resources.
•
Define strategies for local, hybrid, and cloud model execution based on system state, workload requirements, and resource availability.
•
Lead development of telemetry and analytics systems that monitor memory pressure, model utilization, resource contention, and workload efficiency.
•
Partner with operating system, firmware, silicon, and AI framework teams to optimize memory behavior across the full platform stack.
•
Establish technical roadmaps, engineering standards, and architectural guidance across multiple software teams.
•
Mentor senior engineers and architects while influencing company-wide AI platform strategy.
•
Engage with ecosystem partners including Microsoft, Intel, AMD, Qualcomm, NVIDIA, and ISVs to align memory optimization technologies and industry standards.
Education & Experience Recommended
•
Four-year or Graduate Degree in Computer Science, Computer Engineering, Electrical Engineering, Software Engineering, or related technical field, or equivalent experience.
•
12+ years of industry experience in operating systems, systems software, platform architecture, AI infrastructure, 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.
Core Technical Expertise
Memory Systems Architecture
•
Deep expertise in operating system memory management concepts including virtual memory, paging, allocation strategies, memory pressure management, caching, NUMA architectures, and resource isolation.
•
Advanced understanding of DRAM architectures, memory controllers, UMA designs, storage hierarchies, and memory subsystems.
•
Experience optimizing memory behavior for high-performance applications and distributed systems.
AI Memory Optimization
•
Expertise in AI model memory management including:
•
Model residency management
•
Memory budgeting
•
Model quantization
•
Dynamic model loading and unloading
•
Context window optimization
•
Hybrid local/cloud model execution
•
Experience reducing AI memory footprints while maintaining model accuracy and performance.
LLM Runtime Systems
•
Strong knowledge of:
•
KV cache optimization
•
Context management
•
Token generation pipelines
•
Model serving architectures
•
Multi-model execution frameworks
•
Agentic AI runtimes
•
Experience supporting concurrent AI agents sharing compute and memory resources.
Resource Governance & Scheduling
•
Expertise in workload scheduling, admission control, resource allocation, and QoS management.
•
Experience coordinating workloads across heterogeneous compute engines including CPU, GPU, NPU, and cloud services.
•
Understanding of power-aware and thermal-aware resource management techniques.
Performa