Lead Artificial Intelligence Solutions Consultant - Forward Deployed Agentic Engineer

Wells Fargo • Irving, TX

1d • Hybrid

About The Position

Wells Fargo is seeking a Forward Deployed Agentic Lead who will drive the agentic AI products across Chief Operating Office, acting as the bridge between product development, operations, and AI engineering. The role focuses on embedding LLM-powered, agentic workflows directly into enterprise processes, enabling measurable business outcomes, operational transformation, and scalable AI adoption.

Requirements

• 5+ years of Artificial Intelligence Solutions experience, or equivalent demonstrated through one or a combination of the following: work experience, training, military experience, education

Nice To Haves

• Production‑Grade LLM Agent Deployment: Proven experience designing, deploying, and operating LLM‑driven agentic systems in production, with attention to reliability, safety, evaluation, and governance in enterprise environments.
• Deep LLM Platform Expertise: Hands‑on mastery of modern LLMs (GPT‑4/4.1, Claude, Gemini, or equivalents), including model selection, prompt‑to‑model matching, latency/cost optimization, and comparative evaluation.
• LLM Reasoning & Prompt Engineering: Advanced capability in prompt engineering, structured reasoning, chain‑of‑thought management, constrained generation, and output validation for real‑world workflows.
• Agentic LLM Architecture & Orchestration: Strong understanding of LLM‑based agent architectures, including tool calling, function schemas, multi‑agent coordination, planning loops, memory strategies, and guardrails.
• RAG, Context Injection & Knowledge Integration: Practical experience implementing RAG pipelines, embeddings, retrieval strategies, document chunking, re‑ranking, and contextual grounding to reliably augment LLM outputs.
• LLM‑to‑Enterprise Integration: Experience integrating LLM agents with enterprise systems using Python (APIs, databases, SaaS tools, internal services) via MCP or comparable LLM‑integration frameworks.
• Python‑Based Agentic Systems Engineering: Advanced Python proficiency for building production‑grade agentic systems, including planning loops, state management, async execution, and modular service design.
• Customer‑Facing LLM Solution Ownership: Ability to work directly with customers and senior stakeholders to translate business processes into LLM‑powered agentic solutions, define success metrics, and deliver measurable impact.

Responsibilities

• Lead end-to-end deployment of agentic AI solutions into live banking operations
• Embed AI agents directly into operational workflows for automation and decision support
• Work closely with business and operations teams to move from concept to production
• Ensure enterprise-grade deployment, scalability, and governance of AI solutions
• Conduct structured discovery sessions with business and operations stakeholders
• Analyze process artifacts (SOPs, runbooks, workflows, video recordings, process mining outputs, etc.) to identify AI and automation opportunities
• Translate operational processes into agentic workflows and solution blueprints
• Define KPIs and quantify business benefits (cost reduction, cycle time, risk mitigation, productivity gains)
• Build ROI models and value realization frameworks for AI initiatives
• Design and implement agentic AI solutions using process artifacts as input for workflow automation
• Develop multi-step AI agents capable of reasoning, tool use, and task execution
• Leverage MCP (Model Context Protocol) tools to integrate LLMs with enterprise systems, APIs, and data sources
• Enable tool-augmented LLM workflows including function calling, orchestration, and structured outputs
• Build reusable agent patterns for banking operations use cases (e.g., case resolution, reconciliation, compliance checks)
• Hands-on experience with LLM platforms including: Claude (Anthropic), Gemini (Google), GPT (OpenAI)
• Design prompt architectures, reasoning chains, and agent workflows
• Implement RAG (Retrieval-Augmented Generation) and contextual grounding strategies
• Evaluate model performance, reliability, and enterprise readiness
• Ensure responsible AI usage, governance, and compliance adherence
• Build and maintain an Agentic Skills Library of reusable capabilities, including: Task-specific AI agents (e.g., summarization, reconciliation, classification, decision support). Workflow components (e.g., data extraction, validation, routing, reasoning chains). Prompt templates, tool-use patterns, and orchestration blueprints.
• Enable systematic reuse of agentic capabilities across multiple banking use cases.
• Establish standards for versioning, governance, and lifecycle management of agent skills.
• Continuously expand the library based on production learnings and new use cases.
• Drive “build once, reuse everywhere” approach for agentic automation.

Benefits

• Robust benefits
• Competitive compensation
• Programs designed to help you find work-life balance and well-being
• Rewarding investment in your community
• Celebrated for being your authentic self
• Empowered to grow

What This Job Offers

• Job Type: Full-time
• Career Level: Senior
• Education Level: No Education Listed