Senior Software Engineer, AI

Job Description:

Our Technology team drives the evolution of our Engineering, Data, Product and User
Experience functions. Within this group, the GenAI Experiences team builds generative AI
products that define the future of news and business intelligence for millions of users across the
Wall Street Journal and Dow Jones brands. Through our Co-Engineering model, we develop
production-grade AI capabilities — including summarization, conversational AI, and deep
research experiences — in close partnership with Product, Newsrooms, and platform teams.
Collaborating across disciplines, we spearhead the development of groundbreaking AI-powered
products and technologies.

Dow Jones is seeking a Senior Software Engineer to join our GenAI Experiences team in
Barcelona. In this role, you will take end-to-end technical ownership of complex features
and systems, driving delivery with limited supervision and serving as a key technical
contributor on the team. You will partner closely with data scientists, ML engineers, product
managers, and peer engineering leads to design and ship reliable, scalable AI-powered
products.
This is an individual contributor role for an engineer who is ready to lead technically on
large-scope projects, influence engineering direction, and mentor colleagues — while
remaining deeply hands-on in design, implementation, and production operations.

● Design, build, and own end-to-end delivery of AI-powered features across the GenAI
Experiences platform — from backend APIs and data layers to user-facing
integrations.
● Partner with product managers, data scientists, and engineering leads to translate
business requirements into reliable technical solutions, and surfacing risks and
tradeoffs.
● Integrate internal and third-party LLM and AI APIs to extend system functionality
and deliver new product capabilities.
● Develop tools and frameworks for prompt management, automated evaluations, and
observability.

● Improve team processes — code quality standards, testing practices, observability,
and CI/CD pipelines.
● Monitor and improve production AI systems for reliability, performance, and quality
— troubleshooting issues across the full stack.
● Integrate third-party AI APIs (internal and external) to extend the functionality of
systems.
● Participate in code reviews, apply MLOps best practices, and contribute to team
standards for model versioning, experiment tracking, and CI/CD.
● Stay updated on developments in fullstack engineering for GenAI and IR
technologies, incorporating best practices and leveraging cloud infrastructure for
efficiency.

● Bachelor's or Master's degree in Computer Science, Engineering, Data Science, or a related STEM field or equivalent work experience.
● 3-5 years of industry software engineering experience building and operating
production systems.
● Strong Python skills and experience building scalable backend services and REST or
GraphQL APIs.
● Experience with cloud-based infrastructure and services (e.g., AWS and GCP),
Docker, and the Git version control system
● Exposure to deploying and monitoring machine learning models or generative AI
systems in production environments, including automated evaluation pipelines.
● Familiarity with LangChain, LangGraph, LangSmith, or equivalent
agentic/orchestration frameworks.
● Exposure to MLOps tooling — model deployment, monitoring, experiment tracking,
evaluation pipelines — is a strong plus.
● SQL proficiency and experience with data pipeline tooling (Airflow or equivalent).