> Markdown version of [/jobs/ext/3879414-staff-analytics-engineer](https://www.wearedevelopers.com/jobs/ext/3879414-staff-analytics-engineer). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md). --- # Staff Analytics Engineer - **Company:** N able - **Location:** Dundee, UK - **Experience:** Expert - **Contract:** Permanent contract - **Skills:** Artificial Intelligence, Data Analysis, ARM Architecture, Automation of Tests, Continuous Integration, Information Engineering, Data Governance, Python (Programming Language), Power BI, DataOps, SQL Databases, Tableau (Software), Data Logging, Retrieval-Augmented Generation, Large Language Models, Claude Code, Snowflake, Agentic-AI, Build Management, Git Flow, Semantic Modeling, Streamlit Framework - **Published:** October 23, 2026 - **Apply:** https://www.indeed.com/viewjob?jk=840330f0fce24dc6 ## About the Role 8 to 12 years in Business analytics and data engineering, with at least 1 year building semantic models or LLM-grounded analytics, and a track record of shipping data products that other teams reuse. * Deep SQL and dimensional/semantic modeling expertise (facts, dimensions, metrics, conformed entities), with hands-on experience building a semantic layer in Snowflake Semantic Views, dbt Semantic Layer, LookML, or similar. * Hands-on Snowflake experience, ideally including Cortex Analyst, Cortex Agents, and Cortex Search, or comparable text-to-SQL and RAG systems, and a working grasp of why grounding LLMs in governed semantics beats pointing them at raw schema. * Strong Python and analytics-engineering fundamentals across Snowflake dynamic tables, streams, tasks, Snowpark, Git workflows, CI/CD, and automated testing, with the discipline to ship documented, maintainable, reviewable code. * Fluency with AI-assisted coding (Snowflake Cortex Code, Claude Code, or similar) as a daily driver for delivery; spec-driven development experience is a plus. * Proven experience evaluating LLM applications in production: test datasets, LLM-as-a-judge or programmatic scoring and using the results to drive iteration. Familiarity with Monte Carlo or similar data observability platforms is a plus. * Experience building dynamic, interactive data apps (Streamlit or similar) on top of a semantic layer, plus enough Tableau and Power BI to migrate what matters and modernize the reporting estate. * Strong communication skills with a knack for cross-training peers, able to run working sessions with BI analysts, translate ambiguous business asks into precise, certified definitions, and help peers tune the model confidently. ## Description We are looking to hire a senior, hands-on analytics engineer who can bring a strong blend of Snowflake, semantic modelling, SQL, Python and applied AI/LLM experience. We are looking for someone who can do more than traditional BI or data engineering: someone who can build the governed semantic layer that sits behind AI-driven analytics, understand how to evaluate and improve LLM outputs, and turn that foundation into scalable, reusable data products and interactive applications. You need to be technically strong but also comfortable working across BI, data engineering and governance teams, helping analysts adopt and maintain the models rather than becoming a single point of dependency. The role is hybrid requring 2 -3 days a week in our Dundee hub. What You'll Do: * Design and build governed Snowflake Semantic Views (logical tables, relationships, facts, dimensions, metrics, synonyms) as the shared vocabulary AI agents use to answer business questions. * Stand up the evaluation harness for the semantic and agentic layer, including golden-question datasets, LLM-as-a-judge scoring, and side-by-side runs that gate every release. * Build logging, monitoring, and lineage across the layer; partner with data engineering and governance team members on observability for upstream pipelines and data products. * Curate a verified query repository and custom instructions that raise answer accuracy over time. * Ship dynamic Streamlit apps and lightweight data products on top of the semantic layer using AI-assisted coding, modernizing legacy Tableau and Power BI dashboards into faster, interactive experiences. * Crosstrain BI analysts in each domain to tune, extend and maintain their domain models, building the hub-and-spoke that scales this beyond a single team. * Embed governance and data quality by default, partnering with the Data Governance team members to meet certification, stewardship, and CDE requirements.