Platform Engineer: Agentic AI Harness (Partial Remote)

Deutsche Bank AG; Madrid; Hybrid; EUR 90,000 - 130,000; Full time

Job summary

Kyndryl in Madrid is seeking a Platform Engineer to build the internal agent harness: the runtime, orchestration and guardrails that turn foundation models into reliable, governed AI agents at scale.

You will design reusable patterns, define policy‑as‑code oversight, and integrate agents with CI/CD, cloud services, and observability. Strong Python context and cloud-native experience are required.

Qualifications

• 5+ years in Platform Engineering, DevOps or SRE in production.
• Hands-on experience building agent harnesses or agentic systems.
• Strong Python software engineering, production systems and abstractions.
• Cloud-native background: Kubernetes, Containers, IaC and one major cloud.
• Experience with guardrails, SLOs, and evaluation in production environments.

Responsibilities

• Design and build the agent harness: runtime, orchestration, tool and MCP integration, context and memory, evaluation, guardrails and observability.
• Define the oversight model: policy-as-code, human-in-the-loop checkpoints, loop and failure detection, evaluation harnesses, and cost control.
• Integrate agents with the systems they act on: CI-CD, infrastructure, cloud services, observability and ticketing, through APIs and MCP.
• Make agentic productivity measurable: define what productive means for each use case, instrument it, and run the harness on that data.
• Mentor teams, run enablement, and reduce friction between Dev, Ops, Security and the people adopting agents.

Skills

Platform Engineering

DevOps

SRE

Python

Cloud native

Kubernetes

CI/CD

Observability

English/Spanish

Tools

Kyndryl tools

MCP integration

Policy-as-code

Job description

Kyndryl in Madrid is seeking a Platform Engineer to build the internal agent harness: the runtime, orchestration and guardrails that turn foundation models into reliable, governed AI agents at scale.

You will design reusable patterns, define policy‑as‑code oversight, and integrate agents with CI/CD, cloud services, and observability. Strong Python context and cloud-native experience are required.