AI Platform Engineer

About the job

Job Description We are seeking a highly skilled AI Platform Engineer to design, build, and operate our next-generation AI application platform. In this role, you will work on advanced AI systems including Retrieval-Augmented Generation (RAG) pipelines, multi-model gateways, Model Context Protocol (MCP) tools, agentic workflow automations (e.g., n8n), and secure chat interfaces such as OpenWebUI or custom-built solutions. You will be responsible for ensuring the production readiness of all platform components—covering Infrastructure as Code (IaC), CI / CD pipelines, Kubernetes orchestration, observability, cost optimization, and governance. Key Responsibilities • Design, develop, and operate the company’s AI application platform, including RAG pipelines, model gateways, MCP integrations, and agent workflows. • Build and maintain secure chat interfaces using OpenWebUI or custom UI components. • Own IaC (Terraform, Helm, etc.), CI / CD automation, and Kubernetes-based deployments for all AI platform components. • Implement robust observability solutions (monitoring, logging, tracing) across the platform. • Ensure platform reliability, uptime, and scalability using SRE and DevOps best practices. • Optimize compute, storage, and inference costs while maintaining performance and quality. • Establish strong governance, access control, and compliance processes across AI workloads. • Collaborate cross-functionally with product, data science, engineering, and security to deliver high-impact AI features and integrations. • Troubleshoot production issues and continuously improve the platform’s architecture and performance. Required Skills & Qualifications • 4–10+ years of experience in software engineering, DevOps, or AI / ML platform engineering. • Strong hands-on programming experience in Python, Go, or TypeScript. • Expertise with Kubernetes, container orchestration, and cloud-native tooling. • Proficiency with Terraform, Helm, or other IaC frameworks. • Experience building RAG pipelines, LLM integrations, or similar AI workflows. • Familiarity with n8n, LangChain, OpenWebUI, or custom chat interface frameworks. • Solid understanding of observability tools (Prometheus, Grafana, ELK, OpenTelemetry). • Experience with secure, production-grade deployments of AI or distributed systems. Preferred Qualifications • Experience with multi-model routing, inference gateways, or vector databases. • Knowledge of MCP (Model Context Protocol) and related developer tooling. • Prior experience scaling AI or distributed systems in cloud environments (AWS, GCP, Azure). • Understanding of SRE principles, access governance, and security best practices.

Requirements

• Python
• Kubernetes
• Terraform
• AI workflows

Preferred Technologies

• Python
• Kubernetes
• Terraform
• AI workflows