GENERAL INFORMATION

Req #
WD00086686
Career area:
Hardware Engineering
Country/Region:
United States of America
State:
North Carolina
City:
Morrisville
Date:
Wednesday, August 13, 2025
Working time:
Full-time

Additional Locations:

• United States of America - North Carolina - Morrisville

DESCRIPTION AND REQUIREMENTS

Job Summary
We are seeking an experienced and visionary Cloud-Native Architect to lead the technical architecture of our next-generation PaaS platform. The ideal candidate will have deep expertise in container orchestration, distributed systems, microservices governance, and modern DevSecOps, with a strong focus on enabling AI workloads and intelligent agent ecosystems on Kubernetes-native infrastructure.

Key Responsibilities

• Own the end-to-end architecture for our cloud-native platform, including:
• Container Infrastructure – design and optimize scalable, multi-cluster Kubernetes environments with GPU/NPU support.
• AI Compute Scheduling – enable workload-aware GPU resource orchestration, model training/inference separation, elastic scaling, and queue-based job dispatching.
• Model Deployment & Optimization – design patterns for deploying and versioning models (via KServe, Triton, TensorRT), load balancing, A/B testing, and performance tuning.
• Agent Runtime Architecture – define hosting patterns for AI agents built on frameworks like LangChain, Dify, AutoGen, including context caching, vector store binding, and multi-agent collaboration.
• Microservice Governance – service mesh integration (e.g., Istio), observability pipelines, fault injection, and zero-trust inter-service security.
• Serverless Platform – support for FaaS-based AI and edge computing workloads using Knative or OpenFaaS.
• CI/CD and GitOps – build secure and auditable pipelines for both app and model delivery using ArgoCD, Tekton, and policy engines (OPA/Kyverno).
• DevSecOps and Observability – runtime scanning, drift detection, distributed tracing, resource telemetry (including GPU stats).
• AI-native Template & Service Catalog – reusable Helm/Operator-based templates for deploying cloud-native AI workloads (e.g., Jupyter, RAG stack, LLM serving).
• Collaborate with platform engineers, SREs, ML engineers, and product managers to ensure high-performance, secure, and maintainable implementation.
• Lead architecture reviews and evolve internal standards, blueprints, and best practices across teams.
• Track and evaluate emerging technologies in the CNCF ecosystem (e.g., KubeEdge, WASM, eBPF, Gateway API) to inform architectural evolution.
• Align architectural design with compliance, scalability, and hybrid cloud goals.

Qualifications

• 8+ years of experience in software or cloud platform architecture, with 3+ years focused on cloud-native systems.
• with Cloud/AI solution architecture experience would be a plus.
• Expert knowledge of Kubernetes, service mesh, container runtimes, Helm, and multi-cluster management.
• Strong experience with AI infrastructure tooling (e.g., Kubeflow, KServe, MLFlow, Airflow) and GPU/AI workload orchestration.
• Familiarity with LLM agent frameworks (LangChain, Dify, AutoGen) and vector databases (e.g., Milvus, Weaviate, FAISS).
• Proficient in designing CI/CD pipelines, GitOps flows, and DevSecOps integrations.
• Familiarity with OpenShift, Rancher, or similar enterprise container platforms is a plus.
• Strong system design and communication skills; able to align deeply technical decisions with business objectives.
• Bachelor’s or Master’s degree in Computer Science, Engineering, or related field.

We are an Equal Opportunity Employer and do not discriminate against any employee or applicant for employment because of race, color, sex, age, religion, sexual orientation, gender identity, national origin, status as a veteran, and basis of disability or any federal, state, or local protected class.

Additional Locations:

• United States of America - North Carolina - Morrisville
• United States of America
• United States of America - North Carolina
• United States of America - North Carolina - Morrisville

• Own the end-to-end architecture for our cloud-native platform, including:
• Container Infrastructure – design and optimize scalable, multi-cluster Kubernetes environments with GPU/NPU support.
• AI Compute Scheduling – enable workload-aware GPU resource orchestration, model training/inference separation, elastic scaling, and queue-based job dispatching.
• Model Deployment & Optimization – design patterns for deploying and versioning models (via KServe, Triton, TensorRT), load balancing, A/B testing, and performance tuning.
• Agent Runtime Architecture – define hosting patterns for AI agents built on frameworks like LangChain, Dify, AutoGen, including context caching, vector store binding, and multi-agent collaboration.
• Microservice Governance – service mesh integration (e.g., Istio), observability pipelines, fault injection, and zero-trust inter-service security.
• Serverless Platform – support for FaaS-based AI and edge computing workloads using Knative or OpenFaaS.
• CI/CD and GitOps – build secure and auditable pipelines for both app and model delivery using ArgoCD, Tekton, and policy engines (OPA/Kyverno).
• DevSecOps and Observability – runtime scanning, drift detection, distributed tracing, resource telemetry (including GPU stats).
• AI-native Template & Service Catalog – reusable Helm/Operator-based templates for deploying cloud-native AI workloads (e.g., Jupyter, RAG stack, LLM serving).
• Collaborate with platform engineers, SREs, ML engineers, and product managers to ensure high-performance, secure, and maintainable implementation.
• Lead architecture reviews and evolve internal standards, blueprints, and best practices across teams.
• Track and evaluate emerging technologies in the CNCF ecosystem (e.g., KubeEdge, WASM, eBPF, Gateway API) to inform architectural evolution.
• Align architectural design with compliance, scalability, and hybrid cloud goals