Overview
Lead the architecture, design, development and production support of enterprise-grade GenAI and Agentic AI solutions at Wells Fargo.
What you'll do
- Lead the architecture, design, development, testing, deployment, and production support of enterprise-grade GenAI and Agentic AI solutions.
- Design and build AI agents and multi-agent systems capable of planning, reasoning, tool utilization, workflow orchestration, human-in-the-loop execution, and controlled autonomous actions.
- Build solutions leveraging LLMs, foundation models, RAG, embeddings, vector databases, knowledge retrieval, prompt engineering, context engineering, and structured tool/function calling.
- Develop agentic solutions using frameworks such as LangGraph, LangChain, Semantic Kernel, AutoGen, CrewAI or equivalent enterprise AI orchestration frameworks.
- Develop reusable AI components, APIs, services, agent patterns, prompt libraries, evaluation frameworks, and reference implementations.
- Build robust Python-based AI services, APIs, automation capabilities and data-processing pipelines.
- Define technical patterns for integrating GenAI capabilities with enterprise applications, APIs, databases, knowledge stores, engineering platforms, and business workflows.
- Establish engineering approaches for LLMOps/MLOps, AI observability, evaluation, benchmarking, monitoring and production support.
- Implement appropriate AI guardrails addressing hallucination, data leakage, prompt injection, inappropriate tool invocation, access controls and unsafe agent behavior.
- Apply Responsible AI, AI security, privacy, risk, compliance and governance requirements throughout the solution lifecycle.
- Participate in architecture reviews, technical design reviews, code reviews and engineering governance.
- Partner closely with product owners, architects, engineers, cybersecurity, risk, data, platform and business teams to translate business outcomes into appropriate technical solutions.
- Drive engineering excellence through CI/CD, automated testing, DevSecOps, observability, resiliency, performance engineering and operational readiness.
- Diagnose and resolve complex technical problems involving AI models, applications, data, integrations, APIs and agent workflows.
- Mentor engineers and provide technical direction on GenAI, Agentic AI and modern software engineering practices.
- Evaluate emerging AI technologies through hands-on experimentation and convert successful approaches into reusable enterprise patterns.
- Contribute to standards, reference architectures and engineering best practices that enable safe adoption of AI at enterprise scale.
What you'll need
- 5+ years of Specialty Software Engineering or Software Engineering experience, or equivalent demonstrated through work experience, training, military experience, or education, consistent with current Wells Fargo Lead Specialty Software Engineer requirements.
- Strong hands-on software engineering experience using Python and modern application-development practices.
- Demonstrated experience building production-grade Generative AI and/or Agentic AI solutions.
- Strong understanding of LLMs, foundation models, RAG, prompt engineering, embeddings, vector search and AI orchestration.
- Hands-on experience with one or more frameworks such as LangChain, LangGraph, Semantic Kernel, AutoGen, CrewAI or equivalent.
- Experience designing API-based, microservices-oriented and cloud-native architectures.
- Strong understanding of software engineering fundamentals including design patterns, automated testing, API design, CI/CD, security and observability.
- Experience leading technical design and solving complex engineering problems across multiple systems.
Nice to have
- Deep expertise in Agentic AI and multi-agent architectures, including planning, reasoning, memory, tool use, workflow orchestration and human-in-the-loop patterns.
- Experience building enterprise-scale GenAI platforms supporting multiple applications and use cases.
- Experience with LLMOps/MLOps, model evaluation, AI observability and benchmarking.
- Experience with cloud platforms such as Microsoft Azure, Google Cloud Platform or AWS.
- Experience with Kubernetes, containers, microservices, CI/CD, Infrastructure as Code and platform engineering.
- Knowledge of Responsible AI and AI governance, including model risk, privacy, security, auditability and regulatory controls.
- Understanding of AI security practices including prompt-injection defense, adversarial testing, AI red teaming, OWASP guidance for LLM applications, MITRE ATLAS and NIST AI RMF.
- Experience with enterprise knowledge platforms, vector databases, knowledge graphs and semantic search.
- Experience implementing AI observability using platforms such as OpenTelemetry, Splunk or Arize Phoenix.
- Strong technical leadership, communication and mentoring skills.
- Demonstrated ability to convert AI experimentation into secure, governed, reusable production capabilities.
Details
- Location: Bengaluru, India.
- Posting end date: 24 Nov 2026.
Read the full description and apply on the company’s own careers page.