Data Full Stack AI Engineer - W2

About

Miracle Software Systems is looking for a Data Full Stack AI Engineer - W2 with Generative AI to build cutting-edge AI applications powered by Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG).

This role is pivotal in transforming complex system-level data into high-quality, AI-ready data products. The ideal candidate will bridge the gap between backend data orchestration and frontend application development within a robust Google Cloud Platform (GCP) environment.

Core Responsibilities

• Translate complex system level data into business friendly entities and semantic models.
• Design models to enable Generative AI and Agentic AI ready datasets and presentation ready data products within GCP.
• Build and maintain the orchestration, serving, and API integration layers.
• Leverage Cloud Dataflow for stream and batch processing, and Pub/Sub for real-time messaging to support autonomous agent workflows.
• Implement and manage robust CI/CD pipelines using GitHub Actions.
• Automate infrastructure provisioning using Terraform and manage GitHub branching strategies (Dev, Stage, Prod).
• Perform discovery, preparation, and integration of datasets for MVP and production use.
• Integrate requirements with existing enterprise data landing platforms, in both structured and unstructured data formats.
• Work closely with Vertex AI to deploy and manage machine learning models.
• Design data structures that support agentic reasoning, tool calling, and long term memory.
• Develop and maintain data dictionaries and metadata documentation to ensure observability and high data quality for autonomous system grounding.
• Participate in discovery sessions and prototyping phases, mapping end-to-end customer journeys to specific data requirements in collaboration with cross-functional teams.

Technical Skills & Qualifications

• Proficiency in Full Stack development with a strong emphasis on software engineering components (orchestration and serving layers).
• Strong experience in data pipeline development using SQL, Python, Cloud Run, Cloud Functions and Cloud Composer.
• Deep technical knowledge of Data Governance Framework, Data Quality, Metadata Management and Data Security.
• Experience preparing datasets for Vertex AI and building data foundations for Agentic AI frameworks (reasoning, planning, and execution).
• Expert-level experience with GitHub Actions for CI/CD and Terraform for infrastructure management.
• Expertise in dimensional data modeling, semantic layers, and metadata management.
• Expertise in integrating with, and serving to, 3rd-party applications and web portals.