> Markdown version of [/jobs/ext/4759101-manager-ai-deployment-and-runtime](https://www.wearedevelopers.com/jobs/ext/4759101-manager-ai-deployment-and-runtime). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md). --- # Manager, AI Deployment and Runtime - **Company:** Lenovo - **Location:** Morrisville, NC, United States - **Experience:** Expert - **Contract:** Permanent contract - **Skills:** Microsoft Windows, Artificial Intelligence, Application Integration Architecture, C++ (Programming Language), Software Code Optimization, Code Review, Computer Engineering, Device Drivers, Microprocessors, Python (Programming Language), Machine Learning, Language Modeling, Tensorflow, Smart Devices, System Software, Graphics Processing Unit (GPU), Tablet Computers, Discretization, Information Technology, Low Latency, ONNX (Open Neural Network Exchange) Format, Hardware Acceleration, TensorRT, llama.cpp - **Published:** November 17, 2026 - **Apply:** https://jobs.lenovo.com/en_US/careers/Login?jobId=83710 ## About the Role * Education: Master's degree in Electrical & Computer Engineering (ECE), Computer Science, or a related technical field. * Leadership Experience: 4+ years of direct people management experience leading software, machine learning, or embedded engineering teams. * Domain Expertise: Proven track record in deploying and optimizing AI/ML models on client hardware or edge devices (mobile, laptop, embedded systems). * Technical Proficiency: Deep understanding of model optimization frameworks (quantization, distillation, pruning) and edge runtimes (ONNX Runtime, LiteRT, llama.cpp, or platform-specific NPU toolkits). * Strong experience in C++, Python, and cross-platform software design (Windows / Android environments)., * Ph.D. in Electrical & Computer Engineering, Computer Science, or AI/ML domain. * Prior experience managing a team of 10+ engineers using lead/staff delegation models. * Direct experience with NPU acceleration architectures and heterogeneous compute execution on client devices. * Familiarity with privacy-preserving AI frameworks and on-device contextual personalization models. ## Description In this role, you will define the technical strategy, architecture, and operational workflows for deploying, optimizing, and scaling AI models across client hardware, including Lenovo laptops, tablets, and mobile devices. You will bridge deep hands-on technical architecture in edge runtime optimization with strategic engineering leadership-empowering your team, delegating key architecture work through Staff and Lead Engineers, and collaborating closely with cross-functional product, platform, and silicon partner teams., Engineering Leadership & Team Growth * Direct, mentor, and grow a team of 10+ machine learning, systems, and software engineers specializing in AI integration. * Establish team KPIs, engineering standards, code review processes, and Agile delivery cadences to support sustainable growth and direct execution. * Partner with few Tech Leads / Staff Engineers within the team to structure direct reporting lines, establish tech leads per project track, and balance workload distribution. Technical Strategy & On-Device Optimization * Spearhead the deployment and runtime optimization of generative AI, vision, and language models on different devices (laptops, tablets, smartphones). * Drive memory reduction, low-latency inferencing, post-training optimization, and model pruning strategies tailored for resource-constrained client hardware * Optimize execution runtime for heterogeneous compute targets, including NPUs, GPUs, and CPUs (e.g., ONNX Runtime, LiteRT/TensorFlow Lite, llama.cpp) as well as frameworks for different silicon such as OpenVino, NeuroPilot and TensorRT Cross-Functional Collaboration & Ecosystem Engagement * Collaborate with system software, OS kernel, and device driver engineering teams to maximize hardware acceleration on next-generation silicon platforms. * Work closely with product management to translate AI user experiences into concrete model footprint, latency, and throughput specifications. * Engage with external silicon vendors and 3rd party companies to evaluate emerging edge-AI toolchains and hardware capabilities.