Technology Architect – GenAI / Agentic AI Engineer

About the role

Technology Architect – GenAI / Agentic AI Engineer

Location: Charlotte, NC 28202

Work Model: Hybrid – 3 Days Onsite / Week Mandatory

**Experience Required : 15+ Years Required**

Contract Duration: 12 Months

Interview: In-Person / F2F Mandatory

Visa: Open to Visa-Dependent candidates

Role Type: Hands-on Developer / Technology Architect

Job Overview

We are seeking a highly experienced Technology Architect / GenAI Engineer with strong hands-on software development expertise to design, develop, and implement Generative AI, Agentic AI, and Multi-Agent solutions for a banking/financial services environment.

This is a hands-on developer role, not a purely conceptual or architecture-focused position. The successful candidate must be capable of independently writing production-quality Python code, debugging applications, developing AI agents, integrating enterprise tools/APIs, and implementing Model Context Protocol (MCP) solutions.

The candidate should have strong practical experience building and deploying modern GenAI applications and must be comfortable participating in a live coding assessment without code-generation assistance.

Key Responsibilities

Design and develop production-grade Generative AI and Agentic AI applications using Python.

Build autonomous AI agents capable of reasoning, planning, tool usage, task execution, and workflow automation.

Design and implement multi-agent architectures and orchestration patterns for complex enterprise use cases.

Develop AI workflows integrating LLMs with APIs, databases, enterprise applications, and external tools.

Implement and integrate Model Context Protocol (MCP) solutions, including MCP servers, clients, tools, resources, and agent integrations.

Set up MCP environments and connect MCP tools with LLMs and Agentic AI frameworks.

Develop reusable Python components, services, APIs, automation scripts, and AI orchestration workflows.

Troubleshoot and debug Python applications, agent workflows, API integrations, tool-calling issues, and LLM-related failures.

Design and implement RAG-based solutions, including document processing, embeddings, retrieval, ranking, and contextual generation.

Integrate enterprise and cloud-based LLM platforms such as OpenAI/Azure OpenAI, Anthropic, Gemini, or equivalent technologies.

Implement prompt engineering, structured outputs, function/tool calling, memory, context management, and guardrails.

Develop REST/API integrations using frameworks such as FastAPI, Flask, or equivalent.

Evaluate AI-agent performance, reliability, accuracy, latency, and scalability.

Collaborate with engineering, architecture, data, security, and business teams to convert business requirements into production AI solutions.

Ensure solutions meet enterprise security, governance, scalability, and compliance requirements applicable to financial services.

Participate in technical discussions, architecture reviews, coding assessments, and hands-on development activities.

Mandatory Technical Skills

Python Development

Strong hands-on Python programming and scripting experience.

Excellent knowledge of Python development, debugging, exception handling, APIs, data structures, asynchronous programming, and application design.

Ability to independently write and troubleshoot production-quality Python code.

Strong experience developing backend services and automation using Python.

Generative AI

4–5+ years of hands-on Generative AI experience preferred.

Proven experience developing real-world GenAI applications rather than only POCs or theoretical solutions.

Experience with LLM integration, prompt engineering, function/tool calling, structured responses, context management, and LLM application development.

Agentic AI

Strong hands-on experience developing Agentic AI applications.

Experience with autonomous agents, agent tools, planning, reasoning, memory, state management, and task execution.

Practical experience implementing Agentic AI frameworks, such as:

LangGraph

LangChain

AutoGen

CrewAI

Semantic Kernel

or equivalent frameworks.

Multi-Agent Orchestration

Hands-on experience designing and implementing multi-agent systems.

Understanding of agent orchestration, agent-to-agent communication, state management, routing, retries, failure handling, and workflow coordination.

Ability to explain and demonstrate an actual multi-agent implementation.

MCP – Model Context Protocol

Hands-on MCP experience is mandatory.

Strong understanding of Model Context Protocol architecture and implementation.

Experience setting up and configuring MCP servers and clients.

Experience creating and exposing MCP tools/resources.

Experience integrating MCP with LLMs and AI agents.

Ability to troubleshoot MCP connectivity, tool invocation, authentication, and integration issues.

Candidate should be able to explain and demonstrate how they would build an MCP solution from scratch.

AI Workflow & Tool Integration

Hands-on experience building AI-powered workflow automation.

Experience integrating AI agents with:

REST APIs

Databases

Enterprise applications

Cloud services

External tools

Internal business systems

Strong understanding of function calling and tool execution.

RAG / AI Data Technologies

Hands-on experience implementing Retrieval-Augmented Generation (RAG).

Experience with embeddings, vector search, document retrieval, chunking, and contextual retrieval.

Experience with technologies such as:

FAISS

Pinecone

Chroma

Weaviate

Azure AI Search

or equivalent technologies.

API & Backend Development

Strong experience with REST APIs and backend application development.

Experience with FastAPI, Flask, or equivalent Python frameworks.

Strong understanding of API authentication, integration, error handling, and service-to-service communication.

Cloud & Enterprise AI

Experience deploying AI applications in AWS, Azure, or GCP.

Experience with enterprise AI architecture, cloud services, containers, APIs, and production deployments.

Exposure to CI/CD, Docker/Kubernetes, monitoring, and scalable application deployment is preferred.

Banking / Financial Services Experience

Experience working within Banking, Financial Services, FinTech, Payments, Capital Markets, Insurance, or related enterprise environments is strongly preferred.

The candidate should understand the challenges associated with enterprise financial applications, security, data privacy, governance, compliance, and production reliability.

Candidate Expectations

This position requires a self-sufficient hands-on engineer.

The candidate must be able to:

Write Python code independently.

Debug code without assistance.

Build Agentic AI solutions from scratch.

Explain their architecture and implementation decisions.

Demonstrate practical multi-agent development experience.

Explain and implement MCP architecture.

Integrate AI agents with real-world tools and APIs.

Troubleshoot production-level AI workflows.

Clearly explain previous GenAI/Agentic AI implementations.

Candidates with only theoretical knowledge, certifications, POCs, prompt-engineering exposure, or high-level architecture experience without strong coding experience will not be suitable.

Interview & Coding Requirement

In-person/F2F interview is mandatory.

A hands-on coding assessment will be conducted.

The candidate is expected to independently demonstrate:

Python coding

Python debugging

API/tool integration

Agentic AI concepts

Agent orchestration

MCP implementation knowledge

Practical problem-solving

No code assistance will be provided during the coding assessment.

The candidate must be capable of developing and debugging the solution independently.

Experience Requirement

Senior-level / Architect-level experience in software engineering and AI.

Strong hands-on Python development background.

4–5+ years of practical GenAI experience preferred.

Demonstrated production experience with Agentic AI and/or multi-agent systems.

Strong enterprise architecture and development experience.

Candidates with very short or heavily compressed resumes should be avoided; the preferred profile should demonstrate substantial overall technology experience and progressive hands-on development responsibility.

Ideal Candidate Profile

The ideal candidate is a hands-on GenAI/Agentic AI engineer who can also operate at an architect level.

They should be able to take a requirement from:

Business Requirement → AI Architecture → Python Development → Agent Design → MCP/Tool Integration → Multi-Agent Orchestration → Testing/Debugging → Cloud Deployment → Production Support

and independently deliver the solution.

Must-Have Checklist

✅ Strong Python Development

✅ Strong Python Scripting

✅ Production-level Coding & Debugging

✅ 4–5+ Years GenAI hands-on experience

✅ Agentic AI development

✅ Multi-Agent Orchestration

✅ LangGraph/LangChain/AutoGen/CrewAI/Semantic Kernel or equivalent

✅ Hands-on MCP implementation

✅ MCP Server/Client setup

✅ MCP Tool/Resource development

✅ AI Workflow Automation

✅ Tool/API Integration

✅ LLM Integration

✅ RAG

✅ REST APIs / FastAPI / Flask

✅ Cloud/Enterprise AI

✅ Banking/Financial Services experience preferred

✅ F2F interview

✅ Live Coding Test

✅ Self-sufficient developer

✅ Hybrid – 3 Days Onsite in Charlotte, NC