Lead Software Engineer - LLM Suite Engineering - VP

You will lead hands-on engineering efforts to build and enhance the agentic and GenAI capabilities that power the LLM Suite platform. This role offers a mix of deep technical problem-solving, architecture ownership, and collaboration with talented builders. If you enjoy turning ambiguity into reliable production systems, you’ll thrive here. Join a team that values craft, security, and learning.
As a Lead Software Engineer - LLM Suite Engineering at JPMorganChase, you will design and deliver production-grade AI/ML and agentic solutions that integrate seamlessly with existing systems. You will own technical direction across architecture, implementation, and operational stability, with a strong focus on secure, high-quality software. You will partner with peers across engineering to identify patterns and improve standards, reliability, and scalability. You will help evolve the platform using modern public cloud services and agentic frameworks. You will contribute to a collaborative culture through communities of practice and emerging-technology events. You will explore and operationalize emerging patterns such as agent-to-agent communication, model context protocols, and agentic orchestration, turning early-stage concepts into scalable, production-ready capabilities.
Job Responsibilities
Design, develop, and troubleshoot software solutions using creative approaches to solve complex technical challenges
Write secure, high-quality production code and maintain algorithms that integrate with existing systems
Create architecture and design artifacts for complex applications, ensuring design constraints are met through delivery
Build AI/ML solutions and agentic systems for the LLM Suite platform using public cloud architecture (Azure, AWS) and modern agentic frameworks
Implement GenAI services leveraging Azure OpenAI models and AWS Bedrock
Identify hidden problems and patterns in data proactively to improve coding standards and system architecture
Participate in software engineering communities of practice and events focused on emerging technologies
Required Qualifications, Capabilities, and Skills
Computer science degree or equivalent practical experience
Hands-on experience with system design, application development, testing, and operational stability
Proficiency in Python (FastAPI)
Experience building microservices and APIs
Experience with elastic compute, NoSQL databases, and messaging queues
Strong understanding of the Software Development Life Cycle
Solid grasp of CI/CD, application resiliency, and security
Preferred Qualifications, Capabilities, and Skills
Experience implementing GenAI services leveraging Azure OpenAI models and AWS Bedrock
Proficiency working with large language models and building agents with LangGraph
Experience developing, debugging, and maintaining code in a large corporate environment using modern programming and database querying languages
Experience with containerization
Knowledge of agent-to-agent (A2A) communication concepts
Familiarity with Model Context Protocol (MCP)
Experience with agentic orchestrators, personal AI assistants, or AI skills development
About the Team
The LLM Suite Engineering team builds and operates JPMorganChase’s enterprise generative AI platform, enabling teams across the firm to develop, deploy, and scale AI-powered solutions safely and efficiently. The team delivers core platform capabilities such as reusable assistants and workflow automation, secure connections to enterprise knowledge and structured data sources, and model integrations supported by continuous quality benchmarking. Its work is deeply cross-functional, partnering with product, engineering, and control functions to embed security, privacy, access controls, and risk/compliance requirements into the platform by design, while continuously shipping new capabilities that improve reliability, usability, and business impact at global scale.