About This Role
An Analytics Engineer in the Data Infrastructure Team at Prolific transforms and maintains the company's data infrastructure as data work changes rapidly. This role is instrumental in redesigning and scaling the data stack, ensuring data pipelines are robust, efficient, and reliable, and that data is ready to be queried by people and AI systems alike.
Responsibilities
- Build complex dbt models, custom macros, and reusable packages
- Optimize transformations and implement robust testing strategies to ensure data integrity and model performance
- Design and maintain a semantic layer with well-defined metrics, dimensions, and descriptions so that stakeholders and AI assistants can query company data in natural language and get consistent, accurate answers
- Build and productionise LLM-powered steps within pipelines, such as categorizing free text or enriching records, with clear evaluation frameworks, cost and latency monitoring, and fallbacks to keep results trustworthy
- Design and adopt agentic workflows across the analytics engineering lifecycle, including model generation, documentation, test coverage, code review, and incident triage, while defining the guardrails and review processes that keep quality high
- Monitor and maintain dbt workflow jobs, ensuring smooth data refreshes and up-to-date pipelines
- Be responsible for data models powering BI analytics and company-level reporting
- Write tests and assertions to validate data integrity and consistency across models
- Build evaluation sets to measure the accuracy of natural language and LLM-driven outputs
- Create and maintain thorough documentation of dbt processes and semantic definitions, treating metadata as a first-class asset since it directly shapes the quality of AI-generated answers
- Act as a key communicator, translating technical data issues into understandable business terms for stakeholders
- Support junior analysts and data engineers, especially in setting up experimentation platforms, adopting AI tooling responsibly, and following data best practices
- Work closely with product, engineering, and BI teams to ensure data infrastructure supports evolving business needs, including AI-driven products and internal tools
Requirements
- Expertise in dbt & SQL: Deep experience with dbt and SQL to design, build, and maintain scalable data models
- Semantic Modelling: Experience defining metrics, entities, and business logic in a semantic layer (e.g. dbt Semantic Layer/MetricFlow, Cube, LookML or similar), with an understanding of what makes a model reliable for natural language querying
- Applied AI in Data Workflows: Hands-on experience using LLMs in data work, such as classification, extraction, or enrichment within transformations, and an understanding of how to evaluate, test, and govern outputs that aren’t fully deterministic
