Mid Ai/Ml Platform Engineer — Production?Ready Ml

Aily Labs Slu; Madrid; Hybrid; EUR 70,000 - 110,000; Full time

Job summary

Kyndryl is seeking a Platform Engineer to build the internal agent harness—the runtime, orchestration and guardrails that turn foundation models into AI agents doing reliable, governed work at scale. You will treat this harness as a product whose users are the teams building and running agents.

The goal is agentic productivity that can be measured: agents that ship useful work, safely, and keep working when models change.

Qualifications

• 5+ years in Platform Engineering, DevOps or SRE.
• Hands-on experience building agent harnesses or agentic systems.
• Solid Python software engineering for production systems.
• Strong cloud-native background: Kubernetes, containers, IaC, and one major cloud.
• Understanding how LLM agents fail and how to make them reliable.
• Experience treating a platform as a product: contracts, SLOs, adoption metrics.
• Professional working English and Spanish.

Responsibilities

• Design and build the agent harness: runtime, orchestration, tool and MCP integration, context and memory, evaluation, guardrails and observability.
• Build golden paths and reusable patterns so teams ship agents that are reliable, governed and measurable.
• 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.
• Keep the harness model-agnostic and versioned, so it survives model upgrades and provider changes without rewrites.
• Mentor teams, run enablement, and reduce friction between Dev, Ops, Security and the people adopting agents.

Skills

Platform engineering

Agent harness

Python

Kubernetes

Infrastructure as Code

Cloud platforms

LLM reliability

Platform as a product

Bilingual English & Spanish

Job description

Platform Engineer - Agentic AI & Harness Engineering

Partially Remote
Madrid HQ (KES51610)
Full time
R-57624

Who We Are
At Kyndryl, we run and reimagine the mission‑critical technology systems that drive advantage for the world’s leading businesses. We are at the heart of progress; with proven expertise and a continuous flow of AI‑powered insight, enabling smarter decisions, faster innovation, and a lasting competitive edge. For our people‑Kyndryls‑that means doing purposeful work that powers human progress. Join us and experience a flexible, supportive environment where your well‑being is prioritized and your potential can thrive.

**The Role**

We are hiring a **Platform Engineer** to build the internal agent harness: the runtime, orchestration and guardrails that turn foundation models into AI agents doing reliable, governed work at scale. This is harness engineering as a discipline, not a vendor’s product. You build the outer harness around the model, the configuration, tool integration, evaluation and oversight that make agentic productivity real across engineering, infrastructure and operations.

You will treat this harness as a product whose users are the teams building and running agents. The goal is agentic productivity that can be measured: agents that ship useful work, safely, and keep working when the underlying models change.

**What you will do**

• Design and build the agent harness: runtime, orchestration, tool and MCP integration, context and memory, evaluation, guardrails and observability.
• Build golden paths and reusable patterns so teams ship agents that are reliable, governed and measurable, instead of one‑off scripts.
• 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.
• Keep the harness model‑agnostic and versioned, so it survives model upgrades and provider changes without rewrites.
• Mentor teams, run enablement, and reduce friction between Dev, Ops, Security and the people adopting agents.

**What success looks like in your first year**

• Teams ship agents through the harness golden paths instead of bespoke scripts.
• Agentic workflows run in production with guardrails, evaluation and measured productivity impact.
• The harness absorbs at least one model or provider upgrade without a rewrite.

**Who You Are**

**What you will bring**

• 5+ years in Platform Engineering, DevOps or SRE, building developer platforms or runtime and orchestration systems in production.
• Hands‑on experience building agent harnesses or agentic systems: runtime, tool and MCP integration, orchestration, evaluation and guardrails.
• Solid software engineering, primarily in Python, with the depth to build production systems and abstractions, not only prompts.
• Strong cloud‑native background: Kubernetes, containers, Infrastructure as Code, and one major cloud (AWS, Azure or GCP).
• A working grasp of how LLM agents fail and the engineering that makes them reliable: context design, loop and failure detection, verification and evaluation.
• Experience treating a platform as a product: contracts, SLOs, adoption metrics and real users.
• Professional working English and Spanish.

**Nice to have**

• Agent frameworks such as LangGraph, CrewAI, AutoGen etc. and the Model Context Protocol.
• Serious production use of AI‑assisted development tools (Claude Code, Copilot, Codex).
• LLMOps, agent evaluation, or observability for agentic systems.
• Prior work on harnesses that stay stable across model upgrades.
• Platform engineering in regulated environments (finance, insurance, public sector).

**Being You**

The "Kyn" in Kyndryl means kinship, which represents the strong bonds we have with each other, our customers and our communities. We focus on ensuring all Kyndryls feel included and we welcome people of all cultures, backgrounds, and experiences. Even if you don’t meet every requirement, we encourage you to apply. We believe in growth, and we’re excited to see what you can bring. At Kyndryl, employee feedback has told us that our number one driver of employee engagement is belonging. That sense of belonging - being a valued, respected, trusted member of the team - is fundamental to our culture and fueling great experiences for our customers. This dedication to welcoming everyone into our company means that Kyndryl gives you the ability to thrive and contribute to our culture of empathy and shared success. That’s The Kyndryl Way.

**What You Can Expect**

Your career with us isn’t just a job‑it’s an adventure with purpose. We offer a dynamic, hybrid‑friendly culture that supports your well‑being and empowers you to grow. Our Be Well programs are thoughtfully designed to support your financial, mental, physical, and social health‑because we know that when you feel your best, you do your best.

From your very first day, you’ll dive into impactful work that powers the systems our customers rely on every day. You won’t just contribute‑you’ll make a difference, tackling meaningful projects that sharpen your skills and fuel your growth.

We’re here to champion your journey. With powerful tools to chart your career path, personalized development goals aligned with your ambitions, and continuous feedback to keep you inspired and on track, you’ll have everything you need to thrive and evolve. You’ll develop in‑demand skills to grow your career and achieve your ambitions with access to cutting‑edge learning opportunities‑from certifications with Microsoft, Google, and Amazon to coaching and hands‑on experiences. And through it all, you’ll be part of a culture that values empathy, restless learning, and a devotion to shared success.

We want you to thrive here‑and we’re committed to helping you do just that. Ready to make an impact? Join us and help shape what’s next.