[Hiring] Analytics Engineer & AI Specialist @BIX Tecnologia

Role Description

We are looking for someone to join a team that is growing every day, both in size and in professional development. We encourage and believe in our team, and we value working together. If you are someone with a strong team spirit who seeks continuous growth, BIX is the place for you!

Qualifications

• 5+ years of dedicated experience in analytics engineering, data engineering, or a related technical role, with proven cross-functional or client-facing exposure.
• Daily use of AI coding assistants (Cursor, GitHub Copilot, Claude, or equivalent) as a primary development environment is a baseline requirement.
• Advanced SQL mastery (window functions, complex CTEs, incremental pipeline patterns without needing documentation) alongside modern, readable Python for automation workflows and data pipelines.
• Advanced hands-on experience with Snowflake architecture, Dynamic Tables, and Snowflake Cortex (Cortex Analyst, Cortex Agents, Cortex Search).
• Proven track record in building semantic layers (e.g., dbt Semantic Layer, Snowflake Cortex definitions) and structuring datasets, metrics, and YAML/Markdown skill files for seamless ingestion by LLMs and natural language search agents.
• Strong experience building, testing, documenting, and maintaining production-grade dbt projects integrated with CI/CD pipelines and automated QA procedures.
• Fluent English for clear client-facing and cross-functional communication, with an outcome-driven mindset that codifies patterns into reusable templates and thrives in ambiguous environments.

Requirements

• Architect performant, flexible, and secure data models in Snowflake using SQL, Python, and dbt to establish single sources of truth across business domains.
• Build and maintain semantic models using Snowflake Cortex Analyst to expose complex schemas to natural language interfaces, ensuring metrics, dimensions, and relationships allow AI agents to reason correctly.
• Identify and resolve structural, naming, or coverage gaps in datasets that could cause downstream AI agents or LLMs to produce incorrect results.
• Document reusable playbooks, data model templates, and semantic view configurations (YAML/Markdown) that enable non-technical stakeholders or engineers to deploy standardized solutions.
• Oversee data QA, automated testing, data security, permissions, lineage, and definitions to ensure data is structured, trusted, and agent-ready.
• Conduct technical workshops to raise the technical bar for the team and translate complex technical architecture into actionable business insights for client stakeholders.