AI Platform Engineer

Puritas Group; Poland; On-site; PLN 180,000 - 240,000; Full time

Job summary

Puritas Group is seeking an AI Platform Engineer to design, build, and operate enterprise-grade AI platforms across cloud and hybrid environments. You will enable Data Scientists, AI Engineers, and Developers to develop, deploy, monitor, and manage AI workloads.

You will work with AI Architects, Data Engineers, Security and Cloud teams to establish scalable, secure capabilities and strong operational excellence. This role emphasizes platform reliability and cost optimization.

Qualifications

• 4-6 years of experience in Platform Engineering, Cloud Engineering, DevOps, Infrastructure Engineering, or related roles.
• Automated platform provisioning, configuration management, container build, and deployment framework.
• AI/ML CI/CD, GitOps, and MLOps pipeline capabilities.
• Secure, scalable containerized GenAI application hosting for RAG, AI agents, LLM inference, and AI APIs.
• Monitoring, observability, reliability, and incident-management framework.
• Secure and compliant AI platform controls.
• Operational runbooks, platform standards, support documentation, and knowledge transfer.
• Platform performance, capacity, GPU utilization, and cost-optimization recommendations.

Responsibilities

• Enterprise AI platform infrastructure and operating environments built across cloud, hybrid, Kubernetes, and OpenShift platforms.
• Build, deploy, monitor, and support containerized GenAI applications, model-serving services, AI APIs, and inference platforms using OpenShift and Kubernetes.
• Maintain model registries, artifact repositories, pipeline services, development tools, and runtime environments.
• Automate environment provisioning, configuration management, dependency management, and onboarding.
• Ensure platform stability, supportability, and operational readiness.

Skills

Platform Engineering

Cloud Engineering

DevOps

Infrastructure Engineering

CI/CD

GitOps

MLOps

Kubernetes

OpenShift

Security & Compliance

Tools

Kubernetes

OpenShift

KServe

Argo CD

Istio

Helm

Docker

Databricks

Snowflake

Job description

We are seeking a skilled AI Platform Engineer with 4-6 years of experience in designing, implementing, and maintaining the infrastructure, platforms, and tools required to support enterprise AI, Machine Learning, Generative AI, and Agentic AI solutions.

The role will build scalable, secure and reliable AI platforms that enable Data Scientists, AI Engineers, and Developers to efficiently develop, deploy, monitor, and manage AI workloads.

The Engineer will design, deploy, and operate containerized AI and Generative AI platforms using Kubernetes and Red Hat OpenShift, enabling enterprise-grade delivery across cloud and hybrid environments.

The role includes support for GenAI application hosting, LLM inference workloads, Retrieval-Augmented Generation (RAG), AI agents, and API-based AI services.

The successful candidate will collaborate with AI Architects, Data Engineers, Security Teams, and Cloud Engineering teams to establish enterprise-grade AI capabilities and operational excellence.

• Enterprise AI platform infrastructure and operating environments built across cloud, hybrid, Kubernetes, and OpenShift platforms.
• Build, deploy, monitor, and support containerized GenAI applications, model-serving services, AI APIs, and inference platforms using OpenShift and Kubernetes.
• Maintain model registries, artifact repositories, pipeline services, development tools, and runtime environments.
• Automate environment provisioning, configuration management, dependency management, and onboarding.
• Ensure platform stability, supportability, and operational readiness.

Required Skills & Experience

• 4-6 years of experience in Platform Engineering, Cloud Engineering, DevOps, Infrastructure Engineering, or related roles.
• Automated platform provisioning, configuration, container build, and deployment framework.
• AI/ML CI/CD, GitOps, and MLOps pipeline capabilities.
• Secure, scalable containerized GenAI application hosting for RAG, AI agents, LLM inference, and AI APIs.
• Monitoring, observability, reliability, and incident-management framework.
• Secure and compliant AI platform controls.
• Operational runbooks, platform standards, support documentation, and knowledge transfer.
• Platform performance, capacity, GPU utilization, and cost-optimization recommendations.

Preferred Qualifications

• Experience supporting Generative AI and Agentic AI platforms.
• Hands-on experience building and deploying containerized GenAI applications, RAG solutions, AI agents, and LLM-powered services on OpenShift or Kubernetes platforms.
• Experience with OpenShift AI, KServe, model-serving frameworks, vector databases, prompt orchestration, and enterprise GenAI operational frameworks.
• Experience with Databricks, Snowflake, or enterprise data platforms.
• Familiarity with GPU-based workloads, LLM inference, model-serving environments, Helm, Argo CD, and service mesh technologies such as Istio.