Senior Data Engineer ID89366

AgileEngine, LLC.; Perímetro Urbano Manizales; On-site; COP 356,022,000 - 517,850,000; Full time

Benefits offered by this job

Professional growth

Competitive USD-based compensation

Exciting projects

Flextime

Job summary

AgileEngine, LLC. in Colombia is seeking a Senior/Lead Data Engineer to design, build, and maintain pipelines and data models behind a centralized HR data warehouse. You will work with Snowflake, DBT, Python, and Airflow to create semantic layers for BI tools and AI agents.

The role emphasizes reliable data processing, secure data handling, and real-time ingestion from diverse sources, with exposure to Snowflake Cortex and MCP tooling for agentic querying.

Qualifications

• 4+ years of experience in data engineering.
• Snowflake data modeling, datamarts, and data warehouse design.
• DBT for data transformations.
• Python programming and data scripting.
• Airflow for pipeline orchestration.
• REST API integration and data ingestion.
• Google BigQuery querying and optimization.
• Secure handling of large-scale and sensitive data.
• Real-time data processing from diverse sources.
• Strong SQL with optimized queries.

Responsibilities

• Develop and maintain secure, efficient data pipelines using DBT, PySpark, and Python within a cloud environment for HR data sources.
• Build infrastructure and tooling for ETL of data from various sources using Python, DBT, Terraform, and AWS (Glue, EMR, S3).
• Identify and implement internal process improvements, develop tests within the Data Quality Framework, monitor pipelines to 99.5% uptime, and maintain data models for partner teams.
• Design semantic views and ontology layers on top of existing dbt models to make HR data consumable by BI tools and AI agents.
• Develop and deploy AI agents (Snowflake Cortex) for HR use cases enabling natural-language querying over HR data.
• Configure and maintain MCP connections between Snowflake and internal AI tooling to securely expose HR data to conversational interfaces.

Skills

SQL

Python

Airflow

REST API integration

Google BigQuery

Tools

Snowflake

DBT

PySpark

Terraform

AWS

Job description

Manizales, Colombia | Posted on 09/15/2026

WHY JOIN US

If you're looking for a place to grow, make an impact, and work with people who care, we'd love to meet you!

ABOUT THE ROLE

We are looking for a Senior/Lead Data Engineer to build and maintain the pipelines and data models behind a centralized HR data warehouse. Working in Snowflake, DBT, Python, and Airflow, this person designs semantic layers that make HR data consumable by both BI tools and AI agents. Experience with Snowflake Cortex or MCP-based tooling for agentic querying is a strong plus.

WHAT YOU WILL DO

• Develop and maintain secure, efficient data pipelines using DBT, PySpark, and Python applications within a supported cloud environment for HR data sources.
• Build the infrastructure and tooling required for optimal extraction, transformation, and loading of data from a wide variety of sources using Python, DBT, Terraform, and AWS technologies such as Glue, EMR, and S3.
• Identify and implement internal process improvements, develop tests within the Data Quality Framework, monitor pipelines to maintain 99.5% uptime, and create and maintain the data models used by partner teams.
• Design and build semantic views and ontology layers on top of existing dbt models (CORE -> SEMANTIC -> METRICS) so HR data is consumable by both BI tools and AI agents/LLMs, defining business-friendly entities, relationships, and metrics that abstract away raw warehouse structure.
• Develop and deploy AI agents (e.g., via Snowflake Cortex Analyst/Cortex Search) for HR COE use cases — including PE, iCIMS, LMS, and Sales/CS Worker agents — enabling natural-language querying over certified HRDM data.
• Configure and maintain MCP (Model Context Protocol) connections between Snowflake and internal AI tooling to securely expose HR data to conversational and agentic interfaces.

MUST HAVES

• 4+ years of experience.
• Snowflake, including data modeling, datamarts, and data warehouse design.
• DBT for data transformations.
• Python, including object-oriented programming and data scripting.
• Airflow for pipeline orchestration.
• REST API integration and data ingestion.
• Google BigQuery querying and optimization.
• Secure handling of large-scale and sensitive data.
• Real-time data processing (e.g., from Google Sheets or APIs).
• Strong SQL, including highly optimized queries.

NICE TO HAVES

• Semantic layer / semantic modeling design, providing business-object abstraction over dbt and warehouse models.
• Snowflake Cortex (Cortex Analyst, Cortex Search) or equivalent LLM-native query layers.
• MCP (Model Context Protocol) or similar tool-calling / context-exposure frameworks.
• Familiarity with prompt and context engineering for grounding LLM agents in certified data sources.

PERKS AND BENEFITS

• Professional growth: Accelerate your professional journey with mentorship, TechTalks, and personalized growth roadmaps.
• Competitive compensation: We match your ever-growing skills, talent, and contributions with competitive USD-based compensation and budgets for education, fitness, and team activities.
• A selection of exciting projects: Join projects with modern solutions development and top-tier clients that include Fortune 500 enterprises and leading product brands.
• Flextime: Tailor your schedule for an optimal work-life balance, by having the options of working from home and going to the office – whatever makes you the happiest and most productive.