Lead Software Engineer - Agentic AI

JPMorganChase is seeking a Lead Software Engineer - Agentic AI to support the Consumer and Community Banking organization, specifically the Deposits 2.0 platform. In this onsite role in Plano, TX, you will design and lead delivery of an agent-based capabilities platform, partnering across product, engineering, risk, and control stakeholders to translate experimentation into dependable production capabilities.

What you’ll do

• Execute creative software solutions across design, development, and technical troubleshooting, using approaches that go beyond routine patterns to break down complex technical problems.
• Define and drive the platform roadmap for agent-based capabilities, prioritizing measurable outcomes, reliability, and usability.
• Lead end-to-end delivery of core agent platform components, including software development kits, reference implementations, and integration patterns.
• Partner with cross-functional stakeholders to align on requirements, evaluate trade-offs, and remove execution blockers.
• Establish quality, performance, and operational standards for agent workloads, including monitoring, testing, and incident readiness.
• Drive architecture decisions, scalable designs, and repeatable deployment practices to move experimentation into production.
• Embed responsible AI governance into platform design, including privacy and model risk considerations.
• Communicate technical strategy and delivery progress to senior stakeholders using clear data and pragmatic recommendations.
• Promote team adoption of enterprise-authorized AI-assisted engineering practices (such as AI-assisted code review/refactoring, test strategy acceleration, and incident/root-cause analysis support) while establishing consistent validation standards including secure coding, peer review, and automated testing, and encouraging reuse of proven patterns.
• Apply capabilities available within the Software Development Life Cycle toolchain, including enterprise-authorized AI-assisted development and automation, to improve the value realized from automation.

What you bring

• 5+ years of applied experience and formal training or certification on software engineering concepts.
• Proficiency in Python (primary for agent orchestration and LLM tooling) and/or TypeScript, Java, or Go for enterprise backend integration.
• Data and RAG systems expertise, including design of hybrid search pipelines (dense vector retrieval, BM25, rerankers) paired with vector databases such as Pinecone, Milvus, Qdrant, or pgvector.
• Backend and API design experience building scalable microservices using FastAPI, Spring Boot, or Node.js, exposing agent interfaces via REST, WebSockets, and Server-Sent Events for streaming tokens and tool calls.
• Demonstrated experience leading effective use of approved AI-assisted software development tools (for coding, code review, test acceleration, and troubleshooting), including setting team expectations for validating AI outputs for correctness, performance, and security.
• Strong understanding of responsible AI use in engineering workflows, including data sensitivity, secure handling of inputs and outputs, and resiliency and security expectations, including coaching engineers on safe and compliant adoption.
• Production experience with agentic frameworks and orchestration for multi-agent and workflow execution, including LangGraph, AutoGen, CrewAI, LlamaIndex Workflows, and Semantic Kernel.
• Deep expertise in tool calling and function calling, including structuring model tool calls, JSON schema validation, dynamic API integration, sandboxed code execution, and MCP (Model Context Protocol).
• Experience with architecture and memory management, including short-term and episodic memory using scratchpads, state graphs, vector-based retrieval, and conversational buffer compaction.
• LLM foundations including advanced prompt engineering, chain-of-thought, ReAct, reflection loops, and output grounding/guardrails (e.g., NeMo Guardrails, Guardrails AI).

Technologies you may work with

• Python, TypeScript, Java, Go
• Pinecone, Milvus, Qdrant, pgvector
• FastAPI, Spring Boot, Node.js
• REST, WebSockets, Server-Sent Events
• LangGraph, AutoGen, CrewAI, LlamaIndex Workflows, Semantic Kernel
• JSON schema validation, MCP (Model Context Protocol)
• NeMo Guardrails, Guardrails AI
• BM25, dense vector retrieval, rerankers

Additional areas that are a plus

• Experience building agent-based systems, orchestration patterns, or agent development tooling and evaluation frameworks.
• Experience designing scalable inference or model serving architectures, including latency, throughput, and cost optimization.
• Familiarity with responsible artificial intelligence practices, model risk concepts, and governance-by-design approaches.
• Experience contributing to or maintaining widely used open-source software in machine learning or infrastructure ecosystems.
• Domain knowledge applying machine learning to regulated financial services use cases.

About the team

• The Consumer & Community Banking Group relies on innovators to serve consumers, small businesses, municipalities, and non-profits.
• The team supports the delivery of award-winning tools and services spanning personal and small business banking, lending, mortgages, credit cards, payments, auto finance, and investment advice.
• The group also focuses on mobile applications, digital experiences, and next generation banking technology solutions.