Lead Software Engineer, Agentic AI

JPMorgan Chase

Confirmed live today Trusted

Quick summary

Work type: On-site
Location: Jersey City, NJ
Employment: Full-time
Posted: 13 days ago
Freshness: Confirmed live today
Nearby: 99+ roles within 25 mi

Market check

Salary context

How this pay compares to similar roles

Similar $200k

$138k $257k

below market most similar roles pay here above market

This listing doesn't post a salary. Most similar roles pay $164,625–$235,750.

Based on 240 similar postings.

Employer

About JPMorgan Chase

JPMorgan Chase & Co. is a global financial services firm and one of the largest banks in the world, offering investment banking, commercial banking, asset management, and consumer financial services.

JPMorgan Chase currently has 1226 open roles on FindRole.

Listed pay typically runs $156,750–$215,000 across 5 roles with salary data.

Most-posted roles

View all roles at JPMorgan Chase

At a glance

TL;DR · Lead Software Engineer, Agentic AI

Role Posting Log in to save

As a Lead Software Engineer - Agentic AI, Java/Python, you will join the Commercial and Investing Banking - Data Analytics Payments Team to deliver trusted, scalable technology products. You will lead hands-on engineering to build agentic AI on the NEO agent runtime platform, focusing on intelligence automation and data-driven sales growth strategies. Your daily responsibilities include building end-to-end agentic solutions involving sandboxing, memory layers, and retrieval, while delivering full-stack products using Typescript, Next.js, and the Salt Design System. You will utilize Python, React, Kubernetes, Docker, and Terraform to develop secure production code. Key technical tasks involve implementing permission-aware execution, managing LLM-powered systems with RAG architectures, and driving team adoption of AI-assisted engineering practices within a complex financial services IT environment.

Skills

Python Java TypeScript Next.js React Kubernetes Docker Terraform LLM RAG Agentic AI Micro-VMs SSE WebSocket Vector Databases Graph RAG MCP A2A Infrastructure as Code

What you'll do

Build and operate end-to-end agentic solutions on the NEO platform, including execution, sandboxing, and memory layers.
Develop and deliver full-stack products using Typescript, Next.js, and the Salt Design System.
Write, review, and debug secure, high-quality production code across multiple technical areas.
Implement permission-aware, auditable execution for agents with fine-grained authorization and runtime policy checks.
Drive team adoption of enterprise-authorized AI-assisted engineering practices to improve code quality and delivery speed.
Identify and automate the remediation of recurring issues to improve overall operational stability.
Lead communities of practice to drive awareness of leading-edge technologies and mentor senior engineers.

What we're looking for

Formal training or certification on software engineering concepts and 5+ years of applied experience.
Hands-on practical experience delivering system design, application development, testing, and operational stability.
Advanced proficiency in one or more programming languages, with strong Python required.
Experience delivering production React (Next.js) web applications, including real-time UI and design systems.
Demonstrated experience leading the use of approved AI-assisted software development tools and validating AI outputs.
Strong understanding of responsible AI use, data sensitivity, and secure handling of inputs/outputs in engineering workflows.
Hands-on experience building LLM-powered or agentic systems, including tracing, evaluations, and guardrails.
In-depth knowledge of the financial services industry and their IT systems.
Practical cloud native experience with production Kubernetes expected.
Exposure to LLMs, RAG architectures, vector databases, and embedding-based retrieval systems (preferred).
Experience with agent protocols (A2A, MCP) or multi-agent orchestration (preferred).
Experience with sandboxed/secure code execution such as Firecracker, Kata, or gVisor (preferred).
Experience with agent memory or graph-backed retrieval (preferred).
Proficiency with Infrastructure as Code (Terraform) and containerized deployments (Docker, Kubernetes) (preferred).