Senior AI DevOps Engineer

This is a hands-on role for someone who can take AI solutions from idea to production, build the infrastructure around them, and create the observability needed to understand and improve how they behave in the real world.

The project duration is 6 months

. Build and operate production-grade AI agents, AI-enabled tools, and workflows that empower developers and operational teams., Design agentic systems using frameworks such as LangGraph, LangChain, and Supervisor, including RAG, MCP integrations, tool calling, and guardrails., Build and evolve an AI SDLC harness that helps teams plan, implement, validate, govern, and safely deliver AI-assisted software changes., Lead AI observability with Langfuse and OpenTelemetry, including tracing, evaluations, quality measurement, and cost analysis., Build automated evaluation frameworks, including LLM-as-a-judge, to improve the reliability and quality of AI systems., Design and maintain the infrastructure, CI/CD pipelines, GitOps workflows, and security controls that support AI services., Develop internal developer tooling and automation that removes friction across the engineering organization., Partner with engineering and product teams to turn real operational challenges into scalable AI-powered solutions. 5+ years of experience in DevOps, Platform Engineering, SRE, or similar infrastructure-focused roles, Strong coding experience in Python, Go is an advantage, Hands-on experience building or operating production LLM applications and agentic workflows, Experience with LangGraph, LangChain, Supervisor, or similar frameworks, Experience building AI SDLC platforms or harnesses that support the full lifecycle of AI-assisted software delivery, Experience with AI observability and evaluation, preferably Langfuse, OpenTelemetry, and LLM-as-a-judge approaches, Experience with AWS, Kubernetes, Helm, and GitOps CI/CD tools such as GitHub Actions and ArgoCD, Experience building internal developer platforms, DevEx tooling, or engineering automation, Strong ownership, problem-solving skills, and ability to lead cross-team initiatives, Experience with RAG, knowledge bases, MCP, tool calling, and AI guardrails, Experience with Terraform/OpenTofu, Crossplane, and the wider Argo ecosystem, Experience with Datadog, Prometheus, service mesh technologies, or large-scale distributed systems