Indent: SF_OP_208146-1 / SF_OP_208146-2
Role: AI Architect
Location: Charlotte NC (3 days Work from Office)
Max Rate: $78/hr
About the Role
We are seeking a highly experienced AI Architect to lead the design, strategy, and implementation of enterprise-scale AI solutions powered by Agentic AI, LLMs/SLMs, Autonomous Agents, and Generative AI platforms. The role will focus on architecting multi-agent systems, supervisory AI workflows with human-in-the-loop controls, evaluating agentic skills, design integration, workflows, and driving AI-led transformation across data and modernization initiatives. This role requires strong collaboration with business and technology stakeholders to translate AI innovation into scalable, governed, and business-aligned solutions.
Key Responsibilities
- Define architecture and design principles, support planning of technical implementation roadmaps.
- Partner with client stakeholders, Product Owner to identify, prioritize, and shape AI use cases aligned to business and data transformation goals.
- Architect autonomous agent platforms with supervisory controls, human-in-the-loop workflows, governance, and auditability.
- Design multi-agent systems leveraging planning, reasoning, memory, orchestration, and tool-calling capabilities.
- Define agent communication and interoperability frameworks using MCP (Model Context Protocol) and modern AI integration patterns.
- Evaluate and recommend optimal hybrid strategy for LLM/SLM and deterministic approach for enterprise AI applications, automation platforms, and transpiler solutions.
- Research emerging AI technologies, frameworks, and industry trends to provide strategic recommendations.
- Develop AI governance, safety, observability, security, and responsible AI frameworks.
- Define agent mapping, policy recommendations, and operating models for enterprise AI adoption.
- Collaborate with engineering, product, and business teams to establish reusable AI architecture patterns and standards.
- Support executive stakeholders through architecture reviews, technology assessments, workshops, and strategic advisory engagements.
Required Skills & Expertise
Agentic AI & Autonomous Systems
- Multi-Agent Architectures
- Agentic AI Workflows
- Autonomous Agent Platforms
- Human-in-the-Loop AI Systems
- Supervisory AI Architectures
- Agent Planning, Reasoning, and Memory
- Tool Calling & Function Calling
- Agent Governance and Guardrails
- MCP (Model Context Protocol)
Generative AI & Foundation Models
- OpenAI Models
- Anthropic Claude
- Azure OpenAI
- Gemini
- Llama Models
- Large Language Models (LLMs)
- Small Language Models (SLMs)
- Prompt Engineering
- Model Evaluation & Benchmarking
- AI Safety and Responsible AI
AI Engineering & Platform Architecture
- Python
- FastAPI and API-Driven Architectures
- Distributed Systems
- Cloud-Native AI Platforms
- RAG Architectures
- Vector Databases and Semantic Search
- AI Observability and Monitoring
Cloud & Enterprise Platforms
- Microsoft Azure
- AWS
- Google Cloud Platform
- Docker
- Kubernetes
- Terraform
- CI/CD and DevOps Practices
AI Tools & Developer Productivity
Hands-on proficiency with modern AI-assisted engineering tools including:
- Microsoft Copilot
- GitHub Copilot
- Devin
- Claude Code
- AI Coding Agents
- AI-Powered Development Workflows
Knowledge & Retrieval Systems
- Retrieval Augmented Generation (RAG)
- Semantic Search
- Vector Search
- Hybrid Retrieval
- Knowledge Graphs
- Embeddings
- Re-ranking Models
- Context Engineering
Preferred Qualifications
- Experience architecting enterprise AI platforms in regulated environments.
- Experience designing supervisory AI systems with governance and compliance controls.
- Strong understanding of AI risk management, explainability, and policy frameworks.
- Experience with AI-driven modernization, code conversion, transpilers, and automation platforms.
- Knowledge of Data Engineering, Data Governance, Data Quality, Metadata Management, and Analytics ecosystems.
- Cloud Architecture certifications (Azure, AWS, or GCP) preferred.
RAG & Knowledge Intelligence
- Architect enterprise-scale Retrieval-Augmented Generation (RAG) solutions.
- Design hybrid retrieval systems using embeddings, vector search, semantic search, knowledge graphs, and reranking models.
- Build scalable pipelines for document intelligence, metadata discovery, semantic mapping, and contextual reasoning.
- Optimize retrieval quality, latency, grounding, and hallucination mitigation.
Platform Engineering
- Architect cloud-native microservices using Python and FastAPI.
- Design distributed event-driven architectures leveraging APIs, messaging systems, and asynchronous processing.
- Lead implementation of CI/CD, Infrastructure as Code, observability, monitoring, and platform security.
- Ensure production readiness, resiliency, scalability, and cost optimization.
Stakeholder & Team Leadership
- Collaborate with Product Owners, Data Architects, Engineering Teams, Data Scientists, and Business Stakeholders.
- Mentor senior engineers and AI developers on architecture best practices.
- Drive technical decision-making, architecture reviews, and innovation initiatives.
- Support customer engagements, solution workshops, and executive presentations.
Required Technical Skills
Core Engineering
- Expert-level Python development
- FastAPI, Flask, Django
- REST APIs and Microservices Architecture
- Async Programming (asyncio)
- Design Patterns and Clean Architecture
- Distributed Systems Architecture
Agentic AI
- LangGraph
- LangChain
- CrewAI
- AutoGen
- LlamaIndex
- MCP (Model Context Protocol)
- Multi-Agent Orchestration
- Tool Calling and Function Calling
- Agent Memory and Planning Frameworks
Generative AI
- OpenAI
- Azure OpenAI
- Claude
- Gemini
- Llama Models
- Prompt Engineering
- Fine-tuning and Model Evaluation
- AI Safety and Guardrails
RAG & Search
- Retrieval-Augmented Generation (RAG)
- Vector Search Architecture
- Semantic Search
- Hybrid Search
- Embeddings
- Re-ranking Models
- Knowledge Graph Integration
Vector Databases
- Pinecone
- ChromaDB
- Qdrant
- Milvus
- Weaviate
- pgVector
Cloud Platforms
- Microsoft Azure
- AWS
- Google Cloud Platform
Data & Databases
- PostgreSQL
- MongoDB
- SQL Server
- Snowflake
- Databricks
- Data Lake Architectures
DevOps & Platform Engineering
- Docker
- Kubernetes
- OpenShift
- Terraform
- GitHub Actions
- Azure DevOps
- Jenkins
- OpenTelemetry