AI Solution Architect - Chicago, IL- day 1 on-site

Role Summary

The AI Solution architect will define endtoend agent frameworks, ensure alignment with available enterprise environment, guardrails, and partner closely with engineering, QE, security, and compliance teams.

Job Description

 Business & Stakeholder Leadership

• Translate business problems into agentdriven solution blueprints.
• Partner with senior stakeholders to identify highimpact use cases (automation, decision support, quality, operations).
• Provide executivelevel guidance on agentic AI adoption, maturity models, and roadmaps.
• Support client conversations, RFPs, solution pitches, and thought leadership.

Architecture & Design

• Define reference architectures for agentic AI systems (singleagent, multiagent, hierarchical, toolusing agents).
• Design LLMdriven workflows integrating reasoning, planning, memory, tools, and humanintheloop controls.
• Architect RAGbased and toolaugmented agents using enterprise data sources, APIs, and workflows.
• Ensure scalability, resilience, observability, and cost optimization of agent platforms.

Governance, Risk & Guardrails

• Establish AI guardrails covering safety, bias, explainability, auditability, and regulatory compliance.
• Define agent lifecycle management (design, testing, deployment, monitoring, retirement).
• Partner with Risk, Legal, Security, and QE teams to ensure model risk management (MRM) and enterprise readiness.
• Drive standards for agent testing, validation, and certification (functional, nonfunctional, and ethical).

Core AI & GenAI

• Deep expertise in LLMs, prompt engineering, and reasoning frameworks.
• Handson experience with agentic frameworks (e.g., LangGraph, AutoGen, CrewAI, Semantic Kernel, custom agent orchestration).
• Strong understanding of RAG, embeddings, vector databases, and knowledge grounding.
• Experience with finetuning techniques (LoRA / QLoRA) and evaluation strategies.

Architecture & Engineering

• Strong background in distributed systems, APIs, microservices, and cloudnative architectures.
• Proficiency in Python and familiarity with enterprise integration patterns.
• Experience with cloud platforms (Azure, AWS, Google Cloud Platform) and secure enterprise deployments.
• Knowledge of observability, monitoring, and cost management for AI systems.