Senior Specialty Software Engineer - Gen AI

Wells Fargo is seeking a Senior Software Engineer

In this role, you will:

• Lead or participate in complex initiatives on selected domains
• Assure quality, security and compliance for supported systems and applications
• Serve as a technical resource in finding software solutions
• Review and evaluate user needs and determine requirements
• Provide technical support, advice, and consultation with the issues relating to supported applications
• Create test data and conduct interfaces and unit tests
• Design, code, test, debug and document programs using Agile development practices
• Understand and participate to ensure compliance and risk management requirements for supported area are met and work with other stakeholders to implement key risk initiatives
• Conduct research and resolve problems in relation to processes and recommend solutions and process improvements
• Assist other individuals in advanced software development
• Collaborate and consult with peers, colleagues and managers to resolve issues and achieve goals

Required Qualifications:

• 4+ years of Specialty Software Engineering experience, or equivalent demonstrated through one or a combination of the following: work experience, training, military experience, education

Desired Qualifications:

• Architect and build a Valence (CIBX) agentic platform that allows business users to configure, deploy, and manage AI agents without deep technical expertise.
• Design and develop deep agents capable of multi-step planning, tool use, memory, and autonomous task execution (e.g., using frameworks like LangGraph, DeepAgents SDK, or similar).
• Build and optimize Retrieval-Augmented Generation (RAG) pipelines for grounding agent responses in enterprise knowledge bases and documents.
• Integrate Generative AI / LLM capabilities (via internal or third-party model gateways) into scalable backend services.
• Design orchestration layers for routing, planning, task execution, and result aggregation across multiple specialized agents.
• Enable business teams to build agents for automation, analytics, insights, and predictive use cases with reusable templates and configuration-driven workflows.
• Define and implement MCP (Model Context Protocol) or similar tool-calling protocols to connect agents with enterprise systems and APIs.
• Ensure platform scalability, reliability, and observability (logging, monitoring, tracing) for production-grade agentic workloads.
• Collaborate with product, architecture, and business stakeholders to translate BAU pain points into agent-driven automation solutions.
• Mentor junior engineers and drive best practices in agentic system design, prompt engineering, and AI safety/guardrails.
• Contribute to CI/CD pipelines, containerization, and deployment strategy for the platform.

Job Expectations:

• 10-15 years of overall software engineering experience, with strong hands-on Python expertise.
• Proven experience building AI/Generative AI (GenAI) applications in production environments.
• Strong understanding and hands-on experience with RAG (Retrieval-Augmented Generation) architectures - embeddings, vector databases, chunking strategies, retrieval optimization.
• Practical experience building Agentic AI systems - multi-agent orchestration, planning, tool-calling, memory management (e.g., LangChain, LangGraph, AutoGen, CrewAI, DeepAgents, or similar).
• Experience designing low-code/configuration-driven frameworks or platforms for non-technical users.
• Solid understanding of LLM integration patterns (prompt engineering, function/tool calling, streaming responses via SSE/WebSockets).
• Strong API design skills using frameworks like FastAPI/Flask, with experience in asynchronous programming (asyncio).
• Experience with structured logging, observability, and resilience patterns (circuit breakers, retries) in distributed systems.
• Strong problem-solving skills and ability to work in a fast-paced, evolving AI product environment.

Key Responsibilities:

• Architect and build a Valence (CIBX) agentic platform that allows business users to configure, deploy, and manage AI agents without deep technical expertise.
• Design and develop deep agents capable of multi-step planning, tool use, memory, and autonomous task execution (e.g., using frameworks like LangGraph, DeepAgents SDK, or similar).
• Build and optimize Retrieval-Augmented Generation (RAG) pipelines for grounding agent responses in enterprise knowledge bases and documents.
• Integrate Generative AI / LLM capabilities (via internal or third-party model gateways) into scalable backend services.
• Design orchestration layers for routing, planning, task execution, and result aggregation across multiple specialized agents.
• Enable business teams to build agents for automation, analytics, insights, and predictive use cases with reusable templates and configuration-driven workflows.
• Define and implement MCP (Model Context Protocol) or similar tool-calling protocols to connect agents with enterprise systems and APIs.
• Ensure platform scalability, reliability, and observability (logging, monitoring, tracing) for production-grade agentic workloads.
• Collaborate with product, architecture, and business stakeholders to translate BAU pain points into agent-driven automation solutions.
• Mentor junior engineers and drive best practices in agentic system design, prompt engineering, and AI safety/guardrails.
• Contribute to CI/CD pipelines, containerization, and deployment strategy for the platform.

Required Skills & Experience:

• 10-15 years of overall software engineering experience, with strong hands-on Python expertise.
• Proven experience building AI/Generative AI (GenAI) applications in production environments.
• Strong understanding and hands-on experience with RAG (Retrieval-Augmented Generation) architectures - embeddings, vector databases, chunking strategies, retrieval optimization.
• Practical experience building Agentic AI systems - multi-agent orchestration, planning, tool-calling, memory management (e.g., LangChain, LangGraph, AutoGen, CrewAI, DeepAgents, or similar).
• Experience designing low-code/configuration-driven frameworks or platforms for non-technical users.
• Solid understanding of LLM integration patterns (prompt engineering, function/tool calling, streaming responses via SSE/WebSockets).
• Strong API design skills using frameworks like FastAPI/Flask, with experience in asynchronous programming (asyncio).
• Experience with structured logging, observability, and resilience patterns (circuit breakers, retries) in distributed systems.
• Strong problem-solving skills and ability to work in a fast-paced, evolving AI product environment.

Good to Have:

• Experience with OpenShift/Kubernetes for container orchestration and platform deployment.
• Familiarity with MongoDB or other NoSQL databases for state/checkpoint management.
• Exposure to enterprise authentication/authorization patterns (AD/SSO, RBAC).
• Experience with CI/CD tooling (GitHub Actions, Jenkins) and code quality tools (SonarQube).
• Prior experience in financial services / capital markets domain.
• Familiarity with MCP (Model Context Protocol) or similar tool-integration standards.