> Markdown version of [/jobs/ext/4806224-staff-analytics-engineer-semantic-layer-ai](https://www.wearedevelopers.com/jobs/ext/4806224-staff-analytics-engineer-semantic-layer-ai). 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 Semantic Layer AI - **Company:** Kforce Inc. - **Location:** Atlanta, GA, United States - **Experience:** Experienced - **Contract:** Permanent contract - **Skills:** Artificial Intelligence, Amazon Web Services, Data Analysis, Cloud Database, Code Review, Data Architecture, Data Control, Information Engineering, Data Governance, Data Infrastructure, Data Warehousing, Python (Programming Language), PCI Data Security Standards, Search Technologies, Data Processing, Sql Optimization, Large Language Models, Snowflake, Generative AI, Data Lineage, Data Analytics, AWS Data Analytics, Model Context Protocol, Amazon Redshift - **Published:** November 20, 2026 - **Apply:** https://www.dice.com/job-detail/088c250b-c87f-4677-853a-0de42601d23c ## About the Role * 4+ years of experience in data engineering or analytics engineering * 2+ years owning a semantic or metrics layer or establishing modeling standards across multiple teams * Strong hands-on experience with cloud data lakes and data warehouses * Strong experience across AWS data services * Production experience with dbt or an equivalent data modeling framework, including testing, model contracts, and CI * Experience defining modeling standards and enforcing them through CI and code review * Experience reviewing and certifying data models developed by other teams * Experience designing and implementing semantic or metrics layers, such as dbt Semantic Layer, Snowflake Semantic Views, or equivalent technologies * Experience implementing column-level data lineage * Experience developing access controls for sensitive data, including role-based or attribute-based access controls, tag-based masking, and row access policies * Experience separating PCI or similarly sensitive information from broader analytics datasets * Financial services experience, particularly credit card or consumer lending data * Expertise with Amazon Redshift and/or Snowflake * Advanced SQL and Python skills Preferred: * Relevant Snowflake certifications, including SnowPro Core or advanced Data Engineer, Architect, Security Engineer, or Gen AI credentials * Relevant AWS certifications such as AWS Certified Data Engineer, Solutions Architect, Generative AI Developer, or Data Analytics credentials * Experience building LLM or agent-based integrations over governed enterprise data * Experience implementing identity and least-privilege access for AI applications * Experience with Model Context Protocol (MCP) servers * Experience with vector search, semantic search, and Retrieval-Augmented Generation (RAG) * Data platform or major data architecture design experience * PCI DSS knowledge ## Description Kforce has a client that is seeking a Staff Analytics Engineer Semantic Layer AI in Sandy Springs, GA., This person will own semantic-layer standards and help establish the technical requirements for certified enterprise data. The role will work closely with business stakeholders, data governance, and engineering teams to translate agreed business definitions into scalable semantic models, enforce modeling standards, strengthen lineage and sensitive-data controls, and enable governed AI access to certified data. This is a highly hands-on role that combines analytics engineering, data architecture, governance, and emerging AI capabilities., * Assess the existing data platform and modeling practices and identify opportunities to strengthen architecture, standards, and controls * Contribute to data platform architecture decisions and provide data architecture leadership as needed * Establish modeling standards and best practices and enforce them through CI processes and code reviews * Coach engineering and analytics teams on modeling standards and implementation * Build reference or exemplar data models to demonstrate established standards * Translate approved business definitions into fields, metrics, and semantic models * Review and certify models developed by other teams, validating lineage, testing, sensitive-data handling, and query efficiency * Establish and optimize column-level lineage for certified models * Implement controls to separate PCI and other sensitive data from general-purpose datasets using tagging, masking, exclusions, and related approaches * Ensure sensitive data is appropriately controlled within certified and AI-accessible models * Enable AI applications to securely access certified data using appropriate identity and access controls * Build integrations supporting governed AI use cases, including Model Context Protocol (MCP), semantic search, and retrieval-based solutions