Data Engineer - AI

Job Description

Seeking to hire a Data Engineer with 1- 3 years of Data Engineering experience (NOT seeking a Senior Data Engineer).
Full-Time Permanent position (NOT seeking a C2C or Contractor).
Remote work is 100% approved but must be living in the United States (no off-shore).
Requires a US Cit or Green Card Holder.


The ideal candidate is early in their data engineering career and eager to grow into a strong contributor on a modern data platform team. They should be curious, detail-oriented, comfortable learning new tools, and interested in building reliable data foundations that support both traditional analytics and AI-powered insight generation.

Position Summary
We are seeking a Data Engineer to support the development of modern data pipelines, data models, and AI-ready analytics assets. This role will help build and maintain data ingestion workflows using Dagster, transform and model data using dbt, and support the creation of curated MART tables used by internal AI agents for analytics and insight generation.
The Data Engineer will also assist with the development of data schemas, internal tools, and supporting code using Claude Code as part of the development workflow. This role is ideal for someone early in their data engineering career who is interested in modern data platforms, AI-assisted software development, and the use of structured data to power AI agents.
Data produced by these pipelines will be consumed by AI agents in two primary ways: some data will be delivered directly as payloads to the agents, while other data will be retrieved from MART tables through an internal MCP server. AI agents are hosted on AWS Bedrock.


Key Responsibilities

• Assist in building, testing, and maintaining data ingestion pipelines using Dagster.
• Support the orchestration of scheduled, event-driven, and dependency-aware data workflows.
• Develop and maintain dbt models for staging, transformation, and MART-layer data structures.
• Help design and maintain schemas for source data, transformed datasets, MART tables, and AI-agent-facing data structures.
• Write and maintain SQL transformations, tests, documentation, and data quality checks in dbt.
• Support the creation of clean, reliable MART tables that enable analytics, reporting, and AI-driven insights.
• Assist in developing internal tools, utilities, and supporting code using Claude Code as part of the software development process.
• Use Claude Code to accelerate development of data pipeline logic, schema definitions, dbt models, documentation, tests, and internal tooling under the guidance of team members.
• Collaborate with senior product and development teams to define data contracts, pipeline dependencies, schema standards, and transformation patterns.
• Support data delivery patterns for AI agents, including direct payload generation and MART-based retrieval.
• Work with internal teams to ensure data exposed through the MCP server is accurate, well-structured, secure, and fit for AI-agent consumption.
• Assist with troubleshooting pipeline failures, schema mismatches, data quality issues, and transformation errors.
• Learn and apply best practices for data engineering, observability, testing, deployment, and responsible use of AI development tools.
• Collaborate with AI Development teams working with AWS Bedrock-based agents.

Required Qualifications

• Foundational experience with SQL and relational data concepts.
• Basic experience with Python or another scripting language.
• Familiarity with data pipelines, ETL/ELT concepts, APIs, JSON, or structured data formats.
• Interest in data modeling, schema design, analytics engineering, and modern data platforms.
• Ability to troubleshoot issues logically and communicate findings clearly.
• Willingness to learn tools such as Dagster, dbt, Claude Code, AWS services, MCP, and AI-agent data patterns.
• Comfortable working in a collaborative technical environment using Git via Azure DevOps.

Preferred Qualifications

• Exposure to Dagster, Airflow, Prefect, or another orchestration framework.
• Exposure to dbt or analytics engineering workflows.
• Experience creating or maintaining reporting tables, data marts, dimensional models, or semantic data layers.
• Familiarity with schema design, data contracts, validation rules, or metadata documentation.
• Experience using AI-assisted development tools such as Claude Code, GitHub Copilot, ChatGPT, or similar tools.
• Familiarity with cloud platforms, especially AWS.
• Basic understanding of APIs, JSON payloads, MCP-style tool access patterns, and data exchange between systems.
• Interest in AI, large language models, AWS Bedrock, or agent-based analytics systems.
• Basic familiarity with data quality testing, documentation, CI/CD practices, and code review workflows.