Python

JPMorganChase•Jersey City, NJ

About The Position

As a Software Engineer III in Consumer & Community Banking – Wealth Management at JPMorgan Chase, you will join a small, fast-moving AI pod that builds and deploys generative and agentic AI solutions directly with business users. You will work hands-on with LLMs, SLMs, agentic frameworks, and AWS, gain exposure to autonomous AI and agent-to-agent systems, and deliver work that can go live quickly. The role covers developing AI applications from prototype through production, integrating them with internal systems, evaluating their performance, processing large datasets, and deploying secure production code.

Requirements

Formal training or certification in software engineering concepts and at least 3 years of applied experience.
Strong Python skills and hands-on experience with generative AI and AI/ML frameworks.
Bias for action and comfort working to tight timelines.
Hands-on experience using enterprise-authorized AI-assisted software development tools at work, such as for coding, test creation, troubleshooting, or documentation, and ability to critically evaluate, validate, and refine AI-generated outputs for correctness, performance, and security.
Understanding of responsible AI use in engineering workflows, including data sensitivity, secure handling of inputs and outputs, and resiliency and security expectations; ability to guide peers on safe and effective usage within team practices.
Hands-on experience with agent frameworks such as LangGraph, Google ADK, or similar.
Practical experience building LLM-based applications using prompt engineering, skill and tool development, and RAG.
Experience evaluating and benchmarking models or LLM-based applications.
Experience working with large datasets.
Understanding of concurrent, multi-user, and real-time application design.
Experience with AWS or another major cloud platform.
Strong understanding of the SDLC and agile practices, including CI/CD, application resiliency, and security.

Nice To Haves

Exposure to SLMs, LRMs, and model fine-tuning.
Hands-on AI projects, hackathons, or personal builds.
Familiarity with vector databases and streaming architectures.
Front-end experience for AI user experiences.

Responsibilities

Build and ship generative AI and agentic AI applications end to end, from prototype to production.
Develop agentic workflows, including tool-using agents and multi-agent collaboration.
Contribute to autonomous AI capabilities with appropriate guardrails and controls.
Implement orchestration and retrieval-augmented generation (RAG) pipelines, integrating AI solutions with internal systems.
Build and run model and agent evaluations to maintain high-quality outcomes.
Use enterprise-authorized AI coding-assistance tools to improve code quality, delivery speed, and productivity on complex deliverables, validating outputs through peer review, automated testing, and secure coding standards.
Contribute learnings and reusable patterns to improve broader team effectiveness.
Apply knowledge of Software Development Life Cycle toolchain capabilities, including enterprise-authorized AI-assisted development and automation, to improve the value realized by automation.
Process and analyze large datasets that support AI solutions.
Develop components for concurrent, multi-user, and real-time applications.
Write secure, high-quality production code and deploy on AWS using CI/CD.
Partner with business users to gather feedback and iterate quickly.
Contribute to engineering communities of practice and foster a culture of diversity, opportunity, inclusion, and respect.