What are the responsibilities and job description for the Hiring: LLM Platform Engineer for Charlotte, NC (Onsite) position at Key2Source INC?
Job Title: LLM Platform Engineer
Location: Charlotte, NC (Onsite)
Required Skills:
On-premise requirements: (Arize AI, Claude Cowork, Google Cloud Platform, Terraform), Nvidia GPU Environment
Primary Skills
- OpenShift Functions
- OpenShift AI
- Kubernetes
- LLM Deployment & Serving
- Google Cloud Platform
- Terraform
- Arize AI
- Claude Cowork
Key Responsibilities
- Deploy, configure, and manage LLM workloads in on-premise OpenShift environments.
- Design scalable AI/ML infrastructure using OpenShift Functions and Kubernetes.
- Build and optimize enterprise-grade GenAI platforms for inference workloads.
- Implement model deployment, scaling, and monitoring strategies for LLMs.
- Integrate observability and AI monitoring using Arize AI.
- Automate infrastructure provisioning and platform management using Terraform.
- Collaborate with AI/ML engineering teams to operationalize LLM solutions.
- Support hybrid cloud integrations with Google Cloud Platform-based services where applicable.
- Troubleshoot performance bottlenecks in GPU-enabled environments.
Required Qualifications
- Strong hands-on experience with OpenShift/OCP and Kubernetes.
- Experience deploying and managing LLMs in enterprise environments.
- Understanding of AI/ML serving architectures and inference optimization.
- Experience with Terraform and infrastructure automation.
- Knowledge of AI observability and monitoring platforms.
- Familiarity with GenAI ecosystems and enterprise AI workflows.
- Experience with GPU orchestration and NVIDIA-based AI infrastructure.