AI Solution Architect

Role: AI Solution Architect

Location: Chicago, IL, USA (Locals Only)

Exp: Min 11+ yrs

 Visa Independent Candidates

 Mandatory Skills : Generative ai, AWS, Machine Learning, Cloud & Data Engineering

Role Summary & Objectives

•              Translate business automation and efficiency goals into scalable, production-grade AI architectures.

•              Lead the design of autonomous multi-agent systems, complex reasoning loops, and tool-use workflows.

•              Establish robust guardrails, human-in-the-loop decision controls, and system observability.

Key Responsibilities

1. Architecture Design

Build enterprise Generative and Agentic AI platforms featuring high-performance RAG (Retrieval-Augmented Generation) pipelines and vector database integrations.

2. Agent Orchestration

Define multi-agent collaboration patterns, memory management, and autonomous planning frameworks.

3. Governance & Security

Implement data privacy, compliance, risk mitigation, and evaluation guardrails across all AI touchpoints.

4. Cross-functional Leadership

Guide and mentor engineering teams, run discovery workshops with stakeholders, and define reusable deployment patterns.

 Technical Stack & Expertise

Generative AI & Agentic AI

•              Retrieval-Augmented Generation (RAG) pipelines, semantic caching, and context window optimization.

•              Function calling, tool use, and structured data extraction schemas.

•              Evaluation metrics, tracing, and hallucination reduction guardrails.

•              Designing agentic-first workflows and autonomous decision loops.

Multi-Agent Systems

•              Multi-agent coordination patterns (supervisor-worker, decentralized collaboration, stateful graphs).

•              Frameworks like LangChain, LangGraph, and Bedrock Core Runtime for state and memory management.

•              Emerging interoperability standards like Model Context Protocol (MCP) and Agent-to-Agent (A2A) protocols.

Data & Vector Technologies

•              Vector databases (e.g., Milvus, Amazon Aurora PostgreSQL) for high-speed similarity search.

•              Data pipelines and embedding generation workflows using Python, FastAPI, or Apache Spark.

Cloud & Infrastructure

•              Cloud-native deployment on AWS services including Amazon Bedrock, Lambda, EKS, SageMaker, S3, RDS, and DocumentDB.

•              Containerization and orchestration using Docker and Kubernetes.

•              CI/CD pipelines for automated testing of non-deterministic AI outputs.

Observability & Responsible AI

•              Observability and logging pipelines for tracking agent token usage, latency, and failure states.

•              Responsible AI frameworks, data privacy compliance, and bias mitigation guardrails.

Roles & Responsibilities

•              Design and implement enterprise-scale Generative AI and Agentic AI solutions.

•              Develop and optimize RAG-based architectures and autonomous agent systems.

•              Drive AI governance, security, compliance, and operational excellence.

•              Collaborate with business and technical stakeholders to deliver scalable AI solutions.

•              Mentor engineering teams and establish reusable architecture and deployment standards.