About The Position

The Commercial Systems Software Engineering organization is developing HP’s Memory Management platform, a foundational component of the Agentic AI Software Stack that optimizes 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 focuses 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 controls. It calls for deep expertise in operating systems, memory architectures, AI runtime systems, workload scheduling, performance optimization, and large-scale software architecture. The engineer will collaborate with silicon vendors, operating system partners, AI framework teams, product organizations, and ecosystem partners to develop technologies that improve AI performance while maintaining system responsiveness, security, and power efficiency. This company-wide architectural role will help shape the technologies and platform roadmap for future HP AI PCs.

Requirements

  • Four-year or graduate degree in computer science, computer engineering, electrical engineering, software engineering, or a related technical field, or equivalent experience.
  • Typically 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 close to hardware and operating system layers.
  • Deep expertise in operating system memory management, 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.
  • Expertise in AI model memory management, including model residency, memory budgeting, quantization, dynamic model loading and unloading, context window optimization, and hybrid local/cloud execution.
  • Experience reducing AI memory footprints while maintaining model accuracy and performance.
  • Strong knowledge of KV cache optimization, context management, token generation pipelines, model serving architectures, multi-model execution frameworks, and agentic AI runtimes.
  • Experience supporting concurrent AI agents sharing compute and memory resources.
  • 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.
  • Expert-level understanding of performance profiling, bottleneck analysis, workload characterization, and observability systems.
  • Experience building telemetry platforms that generate insights from large-scale performance data.
  • Ability to model and predict system behavior under varying workload conditions.
  • Experience with AI runtimes such as ONNX Runtime, OpenVINO, DirectML, TensorRT, CUDA, ROCm, Qualcomm AI SDKs, or equivalent technologies.
  • Experience optimizing AI inference pipelines on client computing platforms.
  • Familiarity with model compression techniques, including quantization, pruning, distillation, and low-rank adaptation methods.
  • Knowledge of agentic AI frameworks and orchestration systems.
  • Expert proficiency in C++ and Python, with strong systems programming experience.
  • Experience developing operating system services, runtime systems, middleware, or platform software.
  • Familiarity with Windows internals and client platform architecture.
  • Experience building large-scale analytics, telemetry, and automation solutions.
  • Demonstrated technical leadership driving highly complex platform initiatives.
  • Ability to align diverse engineering organizations behind a common architectural vision.
  • Strong cross-functional collaboration across hardware, software, firmware, product, and partner organizations.
  • Exceptional communication skills and ability to influence senior leadership and external partners.
  • Proven mentoring and talent development experience.

Nice To Haves

  • Experience working on operating systems, memory managers, hypervisors, container runtimes, or distributed resource management systems.
  • Prior work on AI PCs, edge AI systems, client computing platforms, or performance-critical infrastructure.
  • Contributions to memory optimization, AI infrastructure, operating systems, or runtime technologies through patents, publications, or open-source projects.

Responsibilities

  • Define and drive the end-to-end architecture for HP’s Memory Management platform.
  • Architect intelligent memory allocation, prioritization, and optimization for AI workloads on client devices.
  • Lead design of model residency management for 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 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 system state, workload requirements, and resource availability.
  • Lead development of telemetry and analytics systems monitoring 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 platform stack.
  • Establish technical roadmaps, engineering standards, and architectural guidance across software teams.
  • Mentor senior engineers and architects and influence 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.

Benefits

  • Health insurance
  • Dental insurance
  • Vision insurance
  • Long-term and short-term disability insurance
  • Employee assistance program
  • Flexible spending account
  • Life insurance
  • Four to twelve weeks of fully paid parental leave based on tenure
  • Eleven paid holidays
  • Flexible paid vacation and sick leave
© 2026 Teal Labs, Inc
Privacy PolicyTerms of Service