AI Engineer

Job Details Information Technology

AI Engineer Dearborn, MI

Posted: 8/25/2026

Job Description

Job #: 64742

Job Category:
Information Technology

Position Type:
Contract

Duration:
Long Term

Remaining Positions: 1

Details:

Stefanini Group is hiring!

Stefanini is looking for an AI Engineer, Dearborn, MI (Onsite)

Responsibilities

• Understand business requirements and develop AI algorithms, models and programs to solve complex problems, generate recommendations, extract patterns, make predictions, interpret sensor data (images, sound), orchestrate automation and enable self-service capabilities.
• Perform large-scale experimentation and develop data driven applications that translate data into actionable intelligence.
• Drive innovative applications of Artificial Intelligence tools and techniques such as deep learning, generative AI, natural language processing, image processing, cognitive automation, intelligent process automation, reinforcement learning, virtual assistants and specialized programming.
• Research and optimize AI technologies to enhance efficiency and accuracy of data analysis and create more efficient automation.
• Architect and deploy the production multi-agent orchestration layer (interpreter/orchestrator, NL-to-SQL agent, visualization agent, RCA/RAG agent, report composition agent, notification agent), using modern agent frameworks with state management and checkpointing rather than ad-hoc loops.
• Design and product ionize RAG pipelines (chunking, embeddings, hybrid retrieval, reranking) grounded in approved schemas, engineering documentation, and historical issue records.
• Own Big Query integration and enforce safe, least-privilege, validated execution of LLM-generated SQL.
• Build CI/CD, containerization, and infrastructure-as-code for deploying agent services on GCP (Cloud Run/GKE, Vertex AI).
• Implement evaluation pipelines and observability/tracing for every agent (golden datasets, LLM-as-judge scoring, regression alerts) so quality is measurable, not assumed.
• Implement guardrails, prompt-injection defenses, and human-in-the-loop approval checkpoints to ensure correctness and safety before any output triggers downstream action.
• Design cost/latency optimization strategies, including tiered model routing (cheap filter models vs. high-capability deep-dive models) and caching.
• Integrate validated outputs with operational systems (Salesforce ticketing, driver/site-manager notifications) and report export pipelines (PDF/HTML/spreadsheet).
• Collaborate with data scientists to product ionize prototypes (anomaly detection, diagnostic agents) into scalable, monitored services.
• Establish versioning, testing, and safe rollout practices (canary/shadow deployments) for evolving agent logic.

Experience Required

• 3+ years building production software systems, including 1–2+ years on ML/AI or LLM-based applications.
• Proven experience designing and deploying multi-agent or multi-service architectures in production environments, beyond notebooks or proof-of-concept demos.
• Strong understanding of distributed systems engineering, including reliability, scalability, service communication, and probabilistic AI components.
• Strong proficiency in Python, including asynchronous and concurrent programming.
• Experience developing backend applications with frameworks such as FastAPI, Flask, or equivalent technologies.
• Hands‑on experience with agent orchestration frameworks such as Lang Graph, CrewAI, Llama Index, or equivalent tools. Experience building stateful, multi‑step, tool‑using agent workflows.
• Practical experience building RAG pipelines: vector databases (pgvector, Pinecone, Weaviate, or Qdrant), embeddings, chunking strategies, and retrieval evaluation.
• Cloud deployment experience, ideally Google Cloud Platform (Big Query, Cloud Run/GKE, Vertex AI, Pub/Sub) or equivalent AWS/Azure services.
• Strong SQL skills and experience with cloud data warehouses. Containerization and CI/CD experience (Docker, Kubernetes, Git Hub Actions/Cloud Build).
• Experience building evaluation and observability pipelines for LLM/agent systems — offline eval sets, LLM‑as‑judge scoring, and tracing tools (Lang Smith, Langfuse, Open Telemetry, or…