Be an integral part of an agile team that's constantly pushing the envelope to enhance, build, and deliver top-notch technology products.
As a Senior Lead Software Engineer- Java/Python/ AI Solutions at JPMorganChase within the Asset and Wealth Management Technology team, you are an integral part of an agile team that works to enhance, build, and deliver trusted market-leading technology products in a secure, stable, and scalable way. Drive significant business impact through your capabilities and contributions, and apply deep technical expertise and problem-solving methodologies to tackle a diverse array of challenges that span multiple technologies and applications.
This is a rare opportunity to help shape the future of our Private Bank. With the sponsorship from the CEO and the heads of the business, our goal is to create an Agentic Private Bank - reimagining the entire process from start to finish, rethinking the operating model including organizational structures and developing AI agents equipped with the latest tools and technologies to fundamentally reshape how we perform this business.
Join our dynamic team of innovators and technologists, where your mission will be to revolutionize how the Bank services and advises clients, deepen client engagements, and drive process transformation. Our culture thrives on experimentation, continuous improvement, and learning. You will work in a collaborative, trusting, and intellectually stimulating environment—one that values diversity of thought and fosters creative solutions that serve the best interests of our global clientele.
Job responsibilities
- Lead the end-to-end design, development, and deployment of client-facing Generative AI and Agentic AI solutions that enhance automation, personalization, and decision-making for external clients.
- Architect and implement prompt-based models on Large Language Models (LLMs) for NLP tasks tailored to financial services use cases such as document summarization, intelligent search, conversational interfaces, and advisory support.
- Design and build autonomous agentic AI workflows capable of multi-step reasoning, tool use, and task execution with appropriate human-in-the-loop guardrails aligned with emerging enterprise patterns such as OpenAI Frontier and Anthropic Claude Cowork
- Implement Model Context Protocol (MCP) integrations to enable AI agents to securely connect to and interact with external data sources, APIs, and enterprise tools in real time.
- Build and maintain scalable data pipelines and data processing workflows for both structured and unstructured data, leveraging cloud services to support LLM-based features and real-time client interactions.
- Design and develop robust APIs and microservices to integrate AI/LLM models into client-facing platforms, ensuring seamless, low-latency experiences.
- Develop secure, high-quality, production-grade code that powers client-facing applications, ensuring reliability, performance, and compliance with financial industry standards.
- Produce architecture and design artifacts for complex, distributed applications while ensuring design constraints, including latency, throughput, and regulatory requirements, are met and implement observability, monitoring, and feedback loops for agentic AI systems to track agent behavior, detect hallucinations, and ensure reliability in high-stakes financial applications
- Gather, analyze, synthesize, and develop visualizations and reporting from large, diverse datasets to inform product improvements, monitor model performance, and enhance client outcomes and proactively identify hidden problems and patterns in data and system behavior, using these insights to drive improvements to code quality, system resilience, and client experience.
- Partner closely with product, design, and business stakeholders to translate client needs and business requirements into scalable AI-driven technical solutions.
- Ensure all client-facing solutions adhere to strict security, privacy, and regulatory standards applicable to the financial services industry, including data protection, model governance, and responsible AI practices, particularly as regulators increase scrutiny of autonomous AI agents in financial services.
Required qualifications, capabilities, and skills
- Formal training or certification in software engineering concepts with 5+ years of applied experience
- Strong programming proficiency in Python or Java, with demonstrated experience building AI/ML-powered applications
- Proven experience designing and developing client-facing applications with a focus on usability, performance, and reliability at scale
- Hands-on experience building data pipelines for both structured and unstructured data processing in support of AI/ML workloads
- Experience developing RESTful APIs and microservices and integrating NLP or LLM models into production software applications
- Hands-on experience with cloud platforms (AWS or Azure) for AI/ML model deployment, data processing, and infrastructure management
- Experience building agentic AI systems with multi-step reasoning, tool orchestration, and autonomous task execution within guardrailed environments
- Familiarity with agentic AI orchestration frameworks such as LangChain, LangGraph, LlamaIndex, Semantic Kernel, CrewAI, AutoGen, or similar libraries
- Strong understanding of security best practices, particularly in the context of client-facing financial applications (e.g., data encryption, access controls, regulatory compliance)
- Solid understanding of the Software Development Life Cycle (SDLC) and agile methodologies including CI/CD, application resiliency, and DevSecOps
- Experience working in a large corporate or financial services environment, with familiarity in navigating complex stakeholder landscapes and regulatory frameworks
Preferred qualifications, capabilities, and skills
- Experience with both Java and Python