Lead AI Software Engineer

Wells Fargo Bank•Mclean, VA

1d•Hybrid

About The Position

Wells Fargo is seeking an AI Engineer to design, build, and deliver AI-enabled applications and agentic systems. The role spans frontend applications, Python backend services, MCP infrastructure, agent workflows, and secure enterprise integrations. The engineer will build user-facing applications and services integrating with Model Context Protocol (MCP) servers, LLM applications, RAG retrieval systems, and agent orchestration platforms, collaborating with AI developers, platform engineers, product teams, and other stakeholders. The position is hybrid and located at 751 Pinnacle Dr., McLean, VA 22102. It is not eligible for visa sponsorship, and relocation assistance is unavailable.

Requirements

At least 5 years of engineering experience, or equivalent demonstrated through work experience, training, military experience, education, or a combination.
At least 5 years of Python proficiency and experience building services with frameworks such as FastMCP, FastAPI, and Flask.
At least 5 years of experience developing and integrating REST APIs, asynchronous services, and event-driven architectures.
At least 5 years of experience integrating AI, LLM-based systems, agent platforms, or AI APIs.
At least 5 years of experience with React and TypeScript for frontend application development.
At least 4 years of experience with authentication, authorization, and access-control patterns, including SSO, OAuth 2.0, API keys, token-based access, RBAC, and scopes.
At least 4 years of experience building or integrating MCP servers and understanding the MCP protocol, including tool registration, schemas, message flows, clients, servers, and lifecycle patterns.
At least 3 years of experience developing agent-driven workflows using LangChain, Google ADK, or similar orchestration frameworks.
At least 3 years of experience with frontend fundamentals, including HTML, CSS, JavaScript, browser rendering, DOM APIs, and performance tuning.
At least 3 years of experience with automated testing using Playwright, performance testing, code reviews, and CI/CD practices.
At least 3 years of experience building secure, scalable, maintainable applications aligned with enterprise platform standards.
Must not require visa sponsorship for this position.

Nice To Haves

Experience building MCP servers using FastMCP or similar Python-based MCP frameworks.
Experience designing MCP-compatible tools, reusable skills, and modular agent capabilities.
Familiarity with tool schema design and structured output validation using Pydantic, JSON Schema, or Zod.
Experience with long-running autonomous agents that support retries, state persistence, error recovery, graceful termination, and multi-step workflow execution.
Experience with RAG-based retrieval systems, vector search, embeddings, or enterprise knowledge retrieval patterns.
Experience with agent observability and tracing tools such as LangSmith, OpenTelemetry, Arize, or similar platforms.
Exposure to Splunk or enterprise observability frameworks.
Experience with Docker, OpenShift, Kubernetes, or similar containerization and deployment platforms.
Experience with Copilot Studio, Microsoft Teams UI integration, or conversational application platforms.
Knowledge of prompt engineering, skill engineering, and knowledge graphs such as llm_wiki and OKF.
Familiarity with secure enterprise software delivery, platform governance, and reusable engineering standards.

Responsibilities

Design, build, and maintain AI-enabled applications using React, TypeScript, Python, and modern API frameworks.
Develop frontend applications that follow enterprise UI standards and reusable component patterns.
Build and maintain Python backend services, APIs, MCP services, and integration layers using frameworks such as FastMCP, FastAPI, and Flask.
Design, implement, and integrate MCP servers and clients for secure context sharing among models, tools, applications, and agent runtimes.
Develop and support agentic workflows for complex, multi-step tasks using frameworks such as LangChain Deep Agents, Google ADK, or similar frameworks.
Build modular, skill-based agents with reusable, composable, and versioned skills.
Create reusable components, services, tool schemas, and integration patterns for enterprise AI applications.
Integrate logging, tracing, and observability frameworks, including Arize- and Splunk-compatible logging and agent observability tooling.
Prepare applications and services for deployment on enterprise container platforms such as OpenShift or Kubernetes.
Deliver end-to-end AI application features using MCP services and agent orchestration layers.
Implement MCP services, including tool schema design, tool registration, API integration, authorization enforcement, and deployment readiness.
Build and maintain MCP-compatible tools, skills, APIs, and UI components for AI applications and agent runtimes.
Integrate AI-powered user interfaces with backend APIs, MCP servers, RAG systems, and agent workflows.
Implement RBAC policies governing which users, agents, clients, and applications can invoke specific tools or services.
Develop agent workflows that support complex user objectives through MCP and skill orchestration.
Align solutions with enterprise standards for application scaffolding, security, observability, logging, testing, and deployment.
Ensure frontend applications are performant, accessible, maintainable, and aligned with reusable design patterns.
Ensure backend and AI services are scalable, observable, secure, and ready for OpenShift or Kubernetes deployment.
Write and maintain technical documentation, integration guides, API specifications, and operational runbooks.
Contribute to code reviews, automated testing, CI/CD, monitoring, and production-support readiness.
Follow applicable Wells Fargo risk and compliance programs, policies, and procedures; proactively monitor and escalate issues and make risk decisions in accordance with requirements.