Artificial Intelligence Engineer

Stefanini Group•Dearborn, MI

1d•Onsite

About The Position

Stefanini Group is seeking a Senior AI & Data Engineer to bridge the gap between scalable data architecture and Generative AI. This role is designed for an engineer who views data as a product and has a proven track record of building production-grade AI-powered applications and agentic workflows. Unlike traditional data modeling roles, this position is responsible for architecting the underlying systems that power the data ecosystem, integrating LLMs, RAG (Retrieval-Augmented Generation) solutions, and autonomous agents into enterprise-scale platforms on Google Cloud (GCP). Stefanini Group is a global provider of offshore, onshore and near shore outsourcing, IT digital consulting, systems integration, application, and strategic staffing services to Fortune 1000 enterprises around the world, with a CMM level 5 rating.

Requirements

7+ years experience in relevant field (Senior Specialist Exp).
6–8 years in Software or Data Engineering, with a strong emphasis on Python-based application development.
2–4 years of hands-on experience building with LLMs, GPT-based APIs, or Vector Databases.
Experience with Fine Tuning LLMs.
Extensive experience with GCP (preferred), including BigQuery, Vertex AI, and Cloud Run.
Experience with Postgres.
Proven ability to design OLTP and OLAP patterns and document complex information flows.
Expert proficiency in Python, SQL, and Terraform.
Experience with MCP (Model Context Protocol), RAG, LangChain, Google Agent Development Kit (ADK).
Rest API development using Flask/Flask API.
Bachelor's Degree.

Responsibilities

Architect and deploy agentic AI workflows and RAG solutions.
Move beyond simple prompting to build systems capable of multi-step reasoning and tool-use.
Design and implement high-performance analytical data products using streaming (Pub/Sub, Dataflow) and batch patterns, ensuring data is "AI-ready."
Own and scale cloud infrastructure using Terraform.
Prioritize security, cost-optimization, and automated environment provisioning.
Build robust pipelines that monitor not just data quality, but AI model performance, latency, and drift in production.
Operate within an Agile environment using Test-Driven Development (TDD).
Maintain rigorous code quality standards via SonarQube, Checkmarx, and Cycode integrated with CI/CD pipelines and GitHub Actions.
Implement enterprise-grade data protection and sharing models.
Map complex data lineages to ensure compliance and traceability.
Provide Tier 3 support for production AI services, ensuring uptime and performance according to established SLAs.