Distinguished Technologist, Edge AI Architect

Own the multi-year technical roadmap and architectural vision for a full-stack Edge AI platform, with a strong focus on orchestrating LLMs, vLMs, and agent-based systems across constrained, on-device, and clustered environments. 

Define the cross-layer architecture and the interface contracts that connect hardware, OS/security, inference, agentic runtime, and model-management layers so the platform operates as a single, coherent, and upgradeable system. 

Architect model management, registry, and lifecycle systems — governing versioning, signing, evaluation, promotion, provenance, and rollback of models across a distributed fleet. 

Set the architecture for agentic AI runtimes and agent-creation tooling — defining how agents are built, sandboxed, permissioned, tool-integrated, governed, and safely operated in production. 

Drive the inference-serving strategy — model serving, inference gateways, and model/request routing — optimized for throughput, latency, and cost across heterogeneous silicon. 

Architect the control plane, end-to-end telemetry, and cost-management frameworks that make on-device and clustered deployments deployable, observable, and manageable at scale. 

Own the security architecture — hardware-rooted chain of trust, secure boot, workload isolation, and sandboxing — ensuring safe execution of agentic workloads. 

Partner deeply with silicon, firmware, and hardware teams to exploit modern compute platforms and build abstraction layers that let AI workloads deploy across diverse silicon without rewrites. 

Architect seamless edge-to-cloud handoff frameworks optimized for cost, latency, privacy, and performance, and define when and how workloads run on-device, at the cluster, or in the cloud. 

Enable multi-modal AI experiences, integrating vision, audio, and text inputs from the runtime through to model management. 

Design scalable on-device lifecycle management frameworks — including deployment, observability, updateability, and manageability — that hold up across a distributed fleet. 

Drive cross-functional influence, bringing together experts across software, firmware, hardware, security, and business teams to converge on a unified platform architecture. 

Communicate technology strategy and the multi-year roadmap to executive leadership, industry partners, and customers, translating deep technical direction into business impact. 

Serve as a trusted technical advisor and the enterprise's top design authority for Edge AI, influencing enterprise-level decision-making through combined technical and business expertise. 

Provide architectural guidance, consultation, and design-review authority across all layers, applications, and platforms, resolving cross-layer trade-offs and setting engineering standards. 

Assess emerging technologies, develop business cases, and shape the platform portfolio in partnership with architects, product leaders, and operations. 

Ensure effective enablement and training for engineering, services, support, and sales teams. 

Mentor and develop emerging technical leaders and architects, fostering a culture of innovation and engineering excellence. 

LLM, vLM, and multi-modal model architecture and orchestration 

Agentic AI systems and runtimes (agent harnesses, tool use, sandboxing, governance) 

Inference serving and optimization (model serving, inference gateways, model/request routing) 

Edge AI and edge-to-cloud architecture (latency, cost, privacy, on-device constraints) 

Model management, registry, lifecycle, versioning, and provenance 

GPU/accelerator computing and heterogeneous silicon (CUDA and related) 

Hardware/software co-design and silicon abstraction layers 

Security foundations: chain of trust, secure boot, isolation, sandboxing, and confidential computing 

Fleet management, control planes, observability, and telemetry 

Distributed systems and scalability 

Kubernetes, Docker, and containerized/microservices architecture 

Python, C++, Rust (systems-level and ML tooling) 

MLOps / LLMOps and CI/CD for models and agents 

Cloud platforms (AWS, Microsoft Azure) and hybrid deployment 

Cost, latency, and performance optimization at scale 

DevOps and automation 

Software engineering and full-stack development 

APIs and interface/contract design across layers