Lead Software Engineer – Data – Agentic Commerce

Overview

In this role you will design and deliver trusted technology for B2B agentic commerce within J.P. Morgan’s Commercial & Investment Bank. You will own end-to-end production agents, from negotiation and onboarding to ML model workflows, driving secure, scalable solutions that advance AI-powered payments. You’ll collaborate with cross-functional teams to improve delivery speed and code quality while shaping innovative payment technology. This is a high-impact opportunity to influence how clients access and use payments technology at scale.

Responsibilities

• Own and design production agents—including orchestration, negotiation, supplier onboarding, and outreach
• Develop production paths for optimization and prediction models (training, automated testing, and serving on Kubernetes)
• Create deterministic agent workflows for pricing, eligibility, and policy decisions
• Write secure, high-quality production code and perform code reviews
• Establish evaluation and observability for agents and models (regression suites, scoring, traces, performance monitoring)
• Prepare agents and models for model risk review with documentation and controls
• Promote enterprise-approved AI-assisted engineering practices to improve quality and speed
• Leverage SDLC tools to enhance automation
• Identify opportunities to automate recurring issues
• Lead evaluation sessions with external vendors, startups, and internal teams to assess designs and credentials

Key requirements

• Formal training or certification in software engineering concepts
• Hands-on experience delivering system design, development, testing, and operational stability
• Advanced proficiency in Python and proficiency in another language (e.g., Java, TypeScript)
• Experience shipping LLM-based applications or agents to production (tool calling, retrieval, evaluation)
• Experience productionizing ML models (training pipelines, model registries, CI/CD for models, API serving)
• Demonstrated experience using AI-assisted software development tools
• Strong understanding of responsible AI use in engineering workflows
• Proficiency across the Software Development Life Cycle
• Advanced understanding of agile methodologies (CI/CD, Application Resiliency, Security)
• Knowledge of the financial services industry and IT systems
• Practical cloud-native experience
• Proficiency with Kubernetes and Amazon EKS, micro-VM isolation, sidecar patterns, with multi-layer security

• collaboration
• problem-solving
• communication
• Python
• Java
• TypeScript

…