AI Platform Engineer: GPU Infra & MLOps

ICE Clear Europe Limited; Georgia; Hybrid; USD 140,000 - 200,000; Full time

Job summary

ICE Clear Europe Limited is seeking an AI Platform Engineer to implement and optimize GPU cluster infra, container tooling, and AI-enabled workflows. You will deploy vector stores, RAG pipelines, and MCP servers, while ensuring secure, scalable operations in a containerized environment.

You will join the AI Platform Operations team, translating architecture decisions into reliable infrastructure, with 24/7 production support and cross-team collaboration.

Qualifications

• Bachelor's degree preferred.
• 3+ years in infrastructure engineering, systems administration, or DevOps.
• 3+ years scripting and automation (Python, Ansible, GitOps).
• 3+ years hands-on Kubernetes in production.
• 2+ years Linux administration.
• Direct experience with GPU infrastructure (NVIDIA preferred).
• 1+ years CUDA exposure.
• 1+ years MCPs exposure.
• 1+ years vector DBs and embedding infra.
• 1+ years RAG pipeline design and deployment.
• 1+ years agent memory patterns (context, external stores).
• 1+ years agentic AI systems orchestration frameworks.
• 1+ years semantic search and embedding models.
• 1+ years workflow/orchestration automation tools.
• Experience with enterprise monitoring & observability tools.
• Ability to work in a service-oriented team environment.
• PM, organization and time management.
• Customer-focused with a strong user experience mindset.
• Clear communication with technical and business resources.
• Fluent English (spoken/written).

Responsibilities

• Deploy, configure, and maintain GPU clusters and related infra.
• Design, build, and maintain AI workflow automation platform.
• Manage NVIDIA drivers, CUDA toolkits, and container runtimes.
• Create and maintain ML framework container images (PyTorch, TensorFlow).
• Implement monitoring, alerting, and observability for GPUs.
• Maintain vector store infra for RAG pipelines and memory.
• Develop end-to-end RAG workflows: ingestion, chunking, embeddings, retrieval.
• Tune agent memory: short/long-term memory and episodic retrieval.
• Deploy and operate Agentic AI systems and orchestration frameworks.
• Host and maintain MCP servers within container platform.
• Manage MCP configs, versioning, access controls, and integration.
• Monitor MCP health, performance, and incidents; perform RCA.
• Develop automation to improve platform reliability and efficiency.
• Provide L2/L3 support and vendor escalation.
• Implement security controls: network policies, RBAC, secrets.
• Execute change requests and document technical details.
• Support production operations in a 24/7 environment.
• Coordinate with developers, operations, release engineers and end-users.
• Educate and mentor team members and ops staff.
• Participate in weekly on-call rotation for after-hours support.

Skills

Python

Ansible

GitOps

Kubernetes

Scripting

Education

Bachelor's degree (preferred)

Tools

NVIDIA GPUs

CUDA

Container runtimes

Vector databases

RAG tooling

MCP servers

CI/CD tooling

Job description

ICE Clear Europe Limited is seeking an AI Platform Engineer to implement and optimize GPU cluster infra, container tooling, and AI-enabled workflows. You will deploy vector stores, RAG pipelines, and MCP servers, while ensuring secure, scalable operations in a containerized environment.

You will join the AI Platform Operations team, translating architecture decisions into reliable infrastructure, with 24/7 production support and cross-team collaboration.