Job Description:

Title: Senior Data Platform Engineer (AI Products)
Location: Dublin, hybrid, 3 days per week in the Storyful office
Type: Hands-on individual contributor / player-coach

Job description

Senior Data Platform Engineer (AI Products)

Storyful is building the next generation of data and AI products on top of complex, high-volume, multi-source content. We are looking for a hands-on Senior Data Platform Engineer to build the technical foundations that make those products scalable, reliable, and ready for production.

This is a senior individual contributor role for someone who is strongest in data engineering but comfortable operating across AI infrastructure, retrieval systems, cloud architecture, and product delivery. You will design and build the ingestion, processing, storage, and serving layers that power future AI and data products across Storyful.

You will work closely with machine learning engineers, software engineers, product managers, and leadership to turn raw structured and unstructured data into trustworthy product capabilities.

What you will do

• Design and build scalable batch and streaming pipelines for structured, semi-structured, and unstructured data

• Own the ingestion and processing architecture for documents, text, metadata, and other content sources

• Build robust data workflows for parsing, chunking, enrichment, indexing, and retrieval

• Create the platform foundations for AI products, including orchestration, data quality, observability, lineage, and cost-aware processing

• Design storage patterns across object stores, relational databases, search/vector systems, and where appropriate graph or knowledge-based systems

• Partner with ML and product engineering to productionise AI features, agentic workflows, and retrieval-backed user experiences

• Define data contracts, schema evolution practices, and quality controls across services and teams

• Improve reliability, freshness, and traceability of pipelines that feed customer-facing products

• Contribute hands-on code while helping set engineering standards and mentoring other engineers

 

What good looks like in this role

• Raw inputs from multiple sources become clean, versioned, monitorable assets that product and ML teams can trust

• New datasets and content types can be onboarded quickly without fragile one-off pipelines

• AI product features are built on observable, debuggable foundations rather than opaque glue code

• Document processing and retrieval quality improve because content is structured well before it reaches the model layer

• The team has clear standards for pipeline reliability, schema management, testing, and deployment

What we’re looking for

• Strong experience in data engineering or platform engineering in production environments

• Excellent Python skills and solid SQL fundamentals

• Experience building reliable ingestion and transformation pipelines at scale

• Strong understanding of data modeling across structured and unstructured datasets

• Experience with workflow orchestration tools such as Airflow, Dagster, Prefect, Temporal, or equivalent

• Strong cloud engineering experience in AWS, GCP, or Azure, with clear transferability across platforms

• Experience with infrastructure as code and modern deployment practices

• Experience with distributed systems, event-driven patterns, and data-intensive applications

• Familiarity with search, vector, or retrieval systems used in AI-backed products

• Ability to work cross-functionally and act as a technical leader without losing hands-on depth

Particularly valuable experience

• Document processing pipelines for PDF, HTML, text, or media-rich content

• Search indexing, retrieval, semantic chunking, or RAG pipeline design

• Graph databases, knowledge graphs, or entity/relationship-heavy systems

• Data quality, lineage, observability, and governance in regulated or high-trust environments

• Experience supporting agentic products with strong guardrails and human-in-the-loop controls

• Experience in media, intelligence, risk, trust, or other information-dense domains

Why this role matters

This role will help Storyful move from promising AI features to durable AI products. The person in this role will lay the foundation that allows ML, GenAI, and agentic capabilities to work reliably on top of real-world data at production scale.

Equal Opportunity Employer

All qualified applicants will receive consideration for employment without regard to race, color, religion, sex, age, national origin, protected veteran status, disability status or any other protected characteristic under applicable law.

Reasonable Accommodation

We are committed to providing reasonable accommodation for qualified individuals with disabilities in our job application and/or interview process. If you need assistance or accommodation in completing your application or participating in an interview due to a disability, email us at [email protected]. Please put "Reasonable Accommodation" in the subject line and provide a brief description of the type of assistance you need. This inbox will not be monitored for application status updates.

Please refer to the privacy notice at the bottom of this page for submitting any data access, deletion, or other data subject rights requests, where permitted under your local laws and regulations.

Business Area:

Dow Jones - Risk

Job Category:

IT Architecture & System Design

Union Status:

 

Base Pay Range: -

We’re committed to offering competitive and flexible compensation to attract top talent. This pay range reflects our good faith estimate for the role and may vary based on a candidate’s experience, skills, location, and other relevant factors.

For bonus-eligible roles, targets are determined based on multiple considerations, including market benchmarks and individual contributions.

For benefits-eligible roles, we offer a comprehensive and competitive benefits package covering health, retirement, wellbeing, and more, along with optional benefits to meet the diverse needs of our employees.