Senior AI Platform Engineer - Agentic Systems

A.P. Moller - Maersk; København; On-site; DKK 900,000 - 1,200,000; Full time

Job summary

Maersk is building an agentic platform enabling engineers to build, deploy and operate agentic systems at scale. You will own platform capabilities end-to-end, tackle reliability, security, performance and cost, and lead experiments with an agent fleet to improve workflows and outcomes across complex, production-grade workloads.

You will collaborate with domain teams, map unfamiliar systems, run experiments, review outputs, and contribute to a durable, reusable platform.

Qualifications

• Shipped agentic systems in production.
• Strong knowledge of distributed systems and security.
• Experience with platform engineering and testing.

Responsibilities

• Own platform capabilities from design through production, including reliability, security, performance and cost.
• Use your agent fleet to explore repositories, implement solutions, build tests and investigate failures.
• Verify agent output through code review, tests, evaluations, traces and benchmarks, and improve workflows when output fails.
• Work with domain teams to understand their needs and turn recurring challenges into reusable tools and platform capabilities.
• Contribute to technical direction by evaluating alternatives, explaining trade-offs and making decisions within your area of ownership.
• Support less experienced engineers through mentoring, pairing and constructive code reviews, helping them build confidence and take ownership.
• Share engineering practices across the team, including how to scope work for agents, challenge their output and verify results.

Skills

Agentic platform

Kubernetes

Observability

Identity & Access

IaC

Tools

LangGraph

Temporal

Dify

AWS

Foundry

Databricks

Job description

Maersk is building an agentic platform enabling engineers to build, deploy and operate agentic systems at scale. You will own platform capabilities end-to-end, tackle reliability, security, performance and cost, and lead experiments with an agent fleet to improve workflows and outcomes across complex, production-grade workloads.

You will collaborate with domain teams, map unfamiliar systems, run experiments, review outputs, and contribute to a durable, reusable platform.