This list contains only the countries for which job offers have been published in the selected language (e.g., in the French version, only job offers written in French are displayed, and in the English version, only those in English).
Wells Fargo is seeking a Senior Specialty AI Engineer to design, build, and productionize GenAI applications end-to-end. You will contribute to the development of LangChain/LangGraph-based workflows, RAG pipelines, and scalable services on Google Vertex AI. You will collaborate with senior engineers and cross-functional teams to deliver reliable, secure, and cost-efficient AI solutions while building depth across architecture, MLOps, and evaluation.
Job Responsibility
Develop multi-step workflows using LangChain and LangGraph (chains, tools, basic state graphs, retries, and error handling)
Implement prompt templates, tool integrations, and memory patterns for GenAI applications
Contribute to observability setup (logging, tracing, prompt/version tracking) and basic guardrails
Build and maintain ingestion pipelines: document parsing, chunking, embeddings, and metadata tagging
Implement retrieval strategies such as dense search, hybrid retrieval (BM25 + vector), and reranking
Configure and manage vector databases (e.g., Pinecone, Weaviate, FAISS)
Develop and deploy services using Google Vertex AI (model endpoints, pipelines, vector search)
Assist in containerization (Docker) and deployment via Kubernetes/GKE
Contribute to CI/CD workflows (GitHub Actions, Cloud Build)
Build backend APIs using Python (FastAPI) or Node.js
Develop user-facing components using React/Next.js
Implement authentication, authorization, and API management (rate limiting, retries)
Work closely with product, data, and platform teams to deliver features
Contribute to engineering best practices (code quality, testing, documentation)
Learn and adopt emerging GenAI tools, frameworks, and patterns
Requirements
4+ years of Specialty Software Engineering experience, or equivalent demonstrated through one or a combination of the following: work experience, training, military experience, education
4 years of AI/ML Software Engineering experience, or equivalent
Hands-on experience with LangChain (required) and exposure to LangGraph or similar orchestration frameworks
Experience building RAG pipelines (chunking, embeddings, retrieval, evaluation basics)
Familiarity with vector databases (Pinecone, Weaviate, FAISS, or similar)
Backend development experience in Python (FastAPI) or Node.js
Frontend experience with React or Next.js
Experience with Docker, basic Kubernetes concepts, and CI/CD pipelines
Understanding of GenAI evaluation concepts, observability basics, and prompt design
Knowledge of security fundamentals (API security, PII handling, secrets management)
Strong problem-solving and communication skills
Nice to have
Exposure to LangGraph advanced patterns (state machines, multi-agent flows)
Experience with LlamaIndex or structured RAG (SQL/Graph RAG)
Familiarity with rerankers (Cohere, bge) and retrieval optimization techniques
Experience integrating LLMs with enterprise tools, databases, or APIs
Basic knowledge of knowledge graphs or ontology design
Exposure to LLM observability tools (LangSmith, OpenTelemetry)