About this role
J.P. Morgan is a global leader in financial services, providing strategic advice and products to the world’s most prominent corporations, governments, wealthy individuals and institutional investors. Our first-class business in a first-class way approach to serving clients drives everything we do. We strive to build trusted, long-term partnerships to help our clients achieve their business objectives.
We recognize that our people are our strength and the diverse talents they bring to our global workforce are directly linked to our success. We are an equal opportunity employer and place a high value on diversity and inclusion at our company. We do not discriminate on the basis of any protected attribute, including race, religion, color, national origin, gender, sexual orientation, gender identity, gender expression, age, marital or veteran status, pregnancy or disability, or any other basis protected under applicable law. We also make reasonable accommodations for applicants’ and employees’ religious practices and beliefs, as well as mental health or physical disability needs. Visit our FAQs for more information about requesting an accommodation.
We have an opportunity to impact your career and provide an adventure where you can push the limits of what's possible. As a Software Engineer III at JPMorganChase within the Commercial and Investment Bank, Payments Technology, you are a seasoned member of an agile team that works to enhance, build, and deliver trusted market-leading technology products in a secure, stable, and scalable way. Based in London, you help build B2B agentic commerce agents that negotiate, onboard, and communicate with corporate suppliers, and the data and machine learning pipelines behind the models those agents call as tools. You deliver on NEO, the firm's governed agent platform for Payments Technology. Job responsibilities
• Executes software solutions, design, development, and technical troubleshooting for agent components, including orchestration logic, agent tools, and task queues for autonomous workflows • Builds and maintains MCP (Model Context Protocol) servers that give agents secure access to CRM, supplier directory, and payments data sources • Develops secure and high-quality production code in Python, and reviews and debugs code written by others • Builds data pipelines and feature engineering jobs on Databricks that prepare payments data for model training and agent retrieval • Contributes to the MLOps path for optimization and prediction models: training jobs, automated tests, and promotion of model artefacts from development through UAT to production • Writes evaluations for agent behaviour (offline test sets, regression suites in CI/CD, LLM-as-judge checks) and instruments services with OpenTelemetry tracing • Applies enterprise-authorized AI-assisted development tools to improve code quality and delivery speed, validating AI outputs for correctness, performance, and security • Identifies opportunities to eliminate or automate remediation of recurring issues to improve the operational stability of agents and model services • Adds to team culture of diversity, opportunity, inclusion, and respect Required qualifications, capabilities, and skills
• Formal training or certification on software engineering concepts and applied experience • Hands-on practical experience in system design, application development, testing, and operational stability • Strong hands-on development experience in Python and/or Java, and ability to code in one or more additional languages (e.g., TypeScript, SQL) • Strong understanding of concurrency and parallelism — multithreading, processes, worker pools, and task queues — and of distributed computation across multiple nodes • Experience building and consuming APIs and event-driven services in a cloud environment • Experience with data processing frameworks such as Apache Spark, and working with large structured datasets • Working knowledge of how LLM-based applications are built: prompting, tool calling, retrieval, and evaluation • Experience using approved AI-assisted software development tools, with sound judgement on validating their outputs • Understanding of responsible AI use in engineering workflows, including data sensitivity and secure handling of inputs and outputs • Solid understanding of agile methodologies such as CI/CD, Application Resiliency, and Security • Practical cloud native experience (AWS preferred), including containers and Kubernetes Preferred qualifications, capabilities, and skills
• Experience with agent frameworks (e.g., Google ADK, LangGraph) and agent protocols such as MCP, A2A, or AG-UI • Experience with Databricks, MLflow, and Delta Lake or Apache Iceberg • Exposure to model serving on Kubernetes and to model monitoring (drift, latency, accuracy) • Familiarity with CRM platforms such as Salesforce and their APIs • Exposure to payments, commercial card, or supplier onboarding (KYC) processes • Familiarity with Terraform and infrastructure as code