Senior AI DevOps Engineer

Quick Facts

• Role: Senior AI DevOps Engineer (hands-on, AI Ops)

• Focus: Production AI agents, AI SDLC infrastructure, observability & evaluation, CI/CD + GitOps, and AI safety

Description

You will build and maintain production AI agents and AI-supported automation for engineering and operations teams. The role designs agentic systems (including RAG and tool calling), develops an AI SDLC platform for safe AI-assisted software delivery, and implements full AI observability and evaluation. You will also own the supporting infrastructure, CI/CD pipelines, GitOps workflows, and security mechanisms for AI services.

Responsibilities

• Create and maintain production AI agents, AI-assisted tools, and automation for engineering and operations

• Design agentic systems using LangGraph, LangChain, Supervisor, including RAG, MCP, tool calling, and AI guardrails

• Build and evolve an AI SDLC platform for planning, deployment, validation, and secure delivery of AI-supported software

• Implement AI observability and evaluation using Langfuse and OpenTelemetry (tracing, evaluations, quality measurement, cost analysis)

• Build automated evaluation frameworks, including LLM-as-a-judge approaches, to improve reliability and quality

• Design and maintain infrastructure, CI/CD pipelines, GitOps workflows, and security mechanisms for AI services

• Develop internal developer tools and automation to remove engineering bottlenecks

• Collaborate with engineering and product teams to translate operational challenges into scalable AI solutions

Requirements

• Minimum 5 years of experience in infrastructure-focused roles (DevOps, Platform Engineering, SRE, or related)

• Excellent Python programming skills (Go is a plus)

• Practical experience building or maintaining production LLM applications and agent workflows

• Experience with LangGraph, LangChain, Supervisor (or similar)

• Experience building AI SDLC platforms supporting the full AI-assisted software delivery lifecycle

• Practical knowledge of AI observability and evaluation (Langfuse, OpenTelemetry, and LLM-as-a-judge preferred)

• Experience with AWS, Kubernetes, Helm, and GitOps CI/CD tools (GitHub Actions, ArgoCD)

• Experience building internal developer platforms (Internal Developer Platforms), DevEx tools, and engineering automation

• Strong ownership, problem-solving skills, and ability to drive cross-team initiatives

Benefits

• Remote work with global flexibility

• Interesting projects tailored to your skills and interests

• B2B contract without an exclusivity clause

• Professional development with modern technologies and varied projects