Full Stack Sr Lead Software Engineer

JPMorganChase•Jersey City, NJ

10d

About The Position

As a Senior Lead Software Engineer at JPMorganChase within Asset and Wealth Management, you will help an agile team build and deliver secure, stable, scalable technology products. You will use deep technical expertise and problem-solving skills to address challenges spanning multiple technologies and applications, while driving significant business impact. This role focuses on architecting and delivering AI-native autonomous agentic AI solutions to transform client onboarding and operational workflows. You will build production-grade agentic AI frameworks, including multi-agent orchestration, retrieval-augmented generation pipelines, dynamic tool-use agents, and LLM-powered reasoning systems, as well as durable, reusable software frameworks for use across teams. You will act as a subject matter expert on agentic AI, advise teams on agent safety, prompt engineering, model evaluation, and responsible AI deployment, and influence senior business, product, and technology stakeholders on adoption of autonomous AI capabilities.

Requirements

Formal training or certification in software engineering concepts and at least 5 years of applied experience.
Experience designing, developing, and maintaining scalable applications using Java/J2EE and/or Python.
Hands-on experience with agentic AI frameworks and deep knowledge of NLP, ML, and cloud-native AI deployment on AWS, including SageMaker and Bedrock.
Experience leading AI-powered products as a Product Owner or Product Manager.
Strong understanding of financial services.
Experience leading integration of AI technologies into existing systems using NLP and ML frameworks.
Experience implementing cloud-based solutions on AWS; EC2, S3, and Lambda are cited.
Demonstrated experience leading effective use of enterprise-authorized AI-assisted software development tools for coding, code review, test acceleration, or troubleshooting.
Ability to establish expectations for validating AI-assisted outputs for correctness, performance, and security.
Understanding of responsible AI use in engineering workflows, including data sensitivity, secure handling of inputs and outputs, resiliency, and security expectations.
Experience coaching senior engineers or leads on compliant AI usage patterns and controls.
Ability to apply expertise and new methods to solve complex technology problems in one or more technical disciplines.
Ability to present and communicate effectively with senior leaders and executives.

Nice To Haves

Expertise in developing and refining prompt engineering and multi-turn agent interaction design.
Expertise in agent observability and evaluation tooling.
Domain knowledge of client onboarding processes.

Responsibilities

Provide technical guidance and direction to support the business and technical teams, contractors, and vendors.
Develop secure, high-quality production code and review and debug code written by others.
Drive adoption and governance of approved AI-assisted engineering practices, establishing measurable validation standards and promoting reuse of proven patterns and automation in the SDLC/TLM toolchain.
Apply Software Development Life Cycle toolchain capabilities, including approved AI-assisted development and automation tools, to improve automation at scale.
Drive decisions influencing product design, application functionality, and technical operations and processes.
Serve as a function-wide subject matter expert in one or more areas of focus.
Advocate for firmwide frameworks, tools, and Software Development Life Cycle practices within the engineering community.
Architect and deliver autonomous agentic AI solutions for client onboarding and operational workflows.
Develop reusable agentic AI frameworks, including multi-agent orchestration, RAG pipelines, dynamic tool-use agents, and LLM-powered reasoning systems.
Advise cross-functional teams on agent safety, prompt engineering, model evaluation, and responsible AI deployment.
Integrate AI technologies into existing systems using NLP and ML to enhance client onboarding and user experience.
Collaborate with data scientists to develop and deploy predictive models.
Implement cloud-based solutions on AWS using services such as EC2, S3, and Lambda.
Champion agile methodologies, facilitating sprint planning, daily stand-ups, and retrospectives.
Set expectations for validating AI-generated outputs for correctness, performance, and security, and coach senior engineers and leads on compliant AI usage patterns and controls.
Communicate effectively with senior leaders and executives.