The scope spans the full stack of a data and AI platform: storage and table formats, pipelines, services, applications, and the agentic systems built on top. You will make the calls on open standards and interoperability, on build against buy, and on how we sequence a migration without disrupting what is already running. You will also set how this organization uses agentic coding, which at this level means building the tooling and the standards that other engineers work within.
The role carries no direct reports. Influence comes from the quality of your designs, the code you ship, and the engineers who get better by working alongside you.
Main Responsibilities
Own the architecture for major platform components and data products, from storage layer through to the application and agent layer.
Define target architectures and the migration paths to reach them, with attention to open standards, interoperability and long-term flexibility.
Write and deploy production code. You will personally build the difficult components and the reference implementations others extend.
Make build against buy decisions with clear reasoning on cost, operational load and dependency risk.
Design the platform foundations that other teams rely on: data contracts, lineage, schema evolution, access control and cost management.
Set the agentic engineering practice across the group, including internal tooling, MCP servers, reusable skills, evaluation harnesses and the standards for reviewing generated code.
Take on the technical problems that are genuinely hard or genuinely ambiguous, and bring them to a working resolution.
Raise the engineering bar through design review, code review and mentoring.
Partner with Product, Business stakeholders and Engineering Managers on sequencing, trade-offs and technical risk.
Core Skills
Programming: Writing code to manipulate, analyze, and visualize data, often using languages like Python, R, and SQL.
AI & Machine Learning: Creating systems that can perform tasks that typically require human intelligence. Using Machine learning (ML), a subset of AI that uses algorithms to learn from and make predictions based on data
Data Analysis: Inspecting, cleansing, transforming, and modeling data to discover useful information, draw conclusions, and support decision-making
Machine Learning Pipelines: Using automated workflows that manage the end-to-end process of training and deploying machine learning models.
Model Deployment: Making a trained machine learning model available for use in production environments.
Required skills
Architecture and system design
Has designed and delivered systems that multiple teams build on, and has lived with the consequences of those decisions.
Strong command of distributed systems fundamentals, including partitioning, consistency models, delivery guarantees, backpressure and schema evolution.
Designs for the non-functional requirements from the start: reliability, recovery, latency, cost, security and operability.
Has migrated live systems to a new architecture while keeping them running.
Writes design documents that another engineer can build from without further explanation.
Data engineering
Platform-level design of table formats and catalogs, covering Iceberg, Delta Lake or Hudi, along with partitioning, clustering, compaction and file layout strategy.
Both batch and streaming architectures, including change data capture and event-driven ingestion.
Transformation frameworks at scale, such as dbt, together with semantic layer design.
Data modelling depth sufficient to set standards that other teams follow.
Performance and cost tuning at platform level, including query engines, storage layout and compute sizing.
Multi-tenant governance, data quality frameworks and lineage.
Software engineering
Deep expertise in at least one language and working fluency in others.
Service and API design, including versioning, backwards compatibility and contract management across teams.
Observability as a design concern: instrumentation, tracing, structured logging and meaningful alerting.
Infrastructure as code using Terraform, Bicep or equivalent, and container orchestration with Kubernetes.
Security practice covering authentication, authorisation, secrets management and data protection.
Front-end capability sufficient to build a usable interface when a product needs one.
AI and agentic engineering
Expert-level use of agentic coding tools. You work through agents for a large share of your output and can explain your harness, your context strategy, how you run work in parallel and how you keep quality high.
Has built tooling that extends what agents can do, such as MCP servers, custom skills, spec-driven workflows or evaluation harnesses.
Has taken large language model systems to production, covering retrieval design, structured output, tool calling, evaluation, guardrails, cost and latency management, and human review where it belongs.
Clear judgement on where a model belongs in a system and where deterministic code is the better answer.
Sets the standard for how generated code is reviewed and how agentic work is verified.
Open source
Meaningful exposure to open source, whether through contributions to established projects, maintaining a project with real users, or substantial public work of your own.
Familiarity with the open standards in this space and a considered view on interoperability.
Public artefacts such as repositories, technical writing or conference talks are a strong signal.
We would be interested to understand from you genuine depth in a minimum two or three of above areas and strong working command across the rest.
What makes you a strong candidate?
Demonstrated work carries the most weight in this role. The strongest candidates can point to systems they designed and built that are running in production, and can explain the decisions behind them, including the ones they would make differently now.
Additional indicators of a strong fit
A track record as a Staff, Principal or Lead engineer who remained hands-on, or as an architect who still writes and deploys code.
Experience being the technical anchor on a platform or product that other teams depended on.
A public body of work: an active GitHub profile with substantial projects, open source contributions, technical writing or talks.
Has introduced a significant technical change into an organisation and carried it through to adoption.
Comfort moving between architectural thinking and detailed implementation within the same week.
#LI-SS1
Maersk is committed to a diverse and inclusive workplace, and we embrace different styles of thinking. Maersk is an equal opportunities employer and welcomes applicants without regard to race, colour, gender, sex, age, religion, creed, national origin, ancestry, citizenship, marital status, sexual orientation, physical or mental disability, medical condition, pregnancy or parental leave, veteran status, gender identity, genetic information, or any other characteristic protected by applicable law. We will consider qualified applicants with criminal histories in a manner consistent with all legal requirements.
We are happy to support your need for any adjustments during the application and hiring process. If you need special assistance or an accommodation to use our website, apply for a position, or to perform a job, please contact us by emailing accommodationrequests@maersk.com.
