Lead Software Engineer - Java/Python/AI/AWS

JPMorganChase•Plano, TX

22h

About The Position

As a Lead Software Engineer at JPMorganChase within Commercial & Community Banking, Marketing Tech, you will contribute to an agile team building secure, stable, and scalable technology products. You will design, build, and maintain an AI agent platform integrating approved models and APIs without model training, including orchestration, tool use, guardrails, and evaluation. The role spans cloud-native AWS infrastructure, production software development in Python and Java, full-stack delivery including React components, integrations, and operational stability. You will also promote enterprise-authorized AI-assisted engineering practices, mentor engineers, and improve the reliability, performance, and cost-effectiveness of platform services.

Requirements

Formal training or certification in software engineering concepts and at least 5 years of applied experience.
Hands-on experience delivering system design, application development, testing, and operational stability for production systems.
Advanced proficiency in Python and/or Java; strong preference for experience with both.
Working knowledge of React and modern frontend fundamentals to contribute to or lead full-stack feature delivery.
Demonstrated end-to-end full-stack engineering across services and APIs, integrations, CI/CD automation, and production operations.
Practical, hands-on AWS experience building cloud-native services across compute, storage, networking, IAM, and observability.
Proficiency across all aspects of the Software Development Life Cycle.
Advanced understanding of agile methodologies, CI/CD, application resiliency, and security-by-design.
Experience leading effective use of approved AI-assisted software development tools for coding, code review, test acceleration, and troubleshooting, including setting validation expectations 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; experience coaching engineers on safe, compliant adoption.
Experience mentoring engineers and leading code and design reviews in an enterprise environment, such as financial services.

Nice To Haves

Experience with Agentic AI or building AI agents using existing models.
Experience with MCP development and tool-integrated agent architectures.
Experience with cloud-native design and delivery on AWS.
Strong hands-on AWS experience across compute, eventing and messaging, and observability.
Strong hands-on Java and Python experience.
Adobe Experience Manager (AEM) knowledge, including author/publish, components/templates, and integrations/APIs.
Experience with CI/CD and production operations, including monitoring, incident support, and root-cause analysis, in enterprise environments.

Responsibilities

Design, build, and maintain an AI agent platform using approved models and APIs, supporting orchestration, tool use, guardrails, and evaluation.
Design and implement software solutions across development and technical troubleshooting, including complex problems beyond routine approaches.
Build and manage cloud-native AWS infrastructure using scalable compute and event-driven patterns, such as ECS containers, serverless services, EventBridge, SNS, and SQS.
Develop secure, high-quality production code in Python and Java; review, debug, and improve code written by others.
Deliver end-to-end full-stack capabilities, including backend services and APIs and React-based UI components where needed.
Build and maintain service interfaces and integrations, including REST APIs, authentication and authorization, and audit and logging patterns.
Create reusable agent components such as prompting patterns, tool connectors, policy and guardrail hooks, and logging and tracing capabilities.
Automate build, deployment, testing, and release processes within the SDLC toolchain, including CI/CD, controls, runbooks, and change management.
Drive adoption of enterprise-authorized AI-assisted engineering practices while enforcing validation standards for secure coding, peer review, and automated testing.
Mentor and guide engineers through design reviews, code reviews, and engineering best practices, and contribute to continuous improvement.
Monitor platform and agent service latency, reliability, and cost; resolve performance and stability issues and prevent recurrence through root-cause fixes or automated remediation.