Senior Lead Software Engineer, Python Distributed Development and AI Modernization

JPMorgan Chase

Confirmed live yesterday High trust

Quick summary

Work type: On-site
Location: Jersey City, NJ
Posted: 30 days ago
Freshness: Confirmed live yesterday
Nearby: 99+ roles within 25 mi

Market check

Salary context

How this pay compares to similar roles

Similar $212k

$187k most similar roles pay here $237k

This listing doesn't post a salary. Most similar roles pay $192,050–$232,262.

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 1117 open roles on FindRole.

Listed pay typically runs $186,160–$215,000 across 7 roles with salary data.

Most-posted roles

View all roles at JPMorgan Chase

At a glance

TL;DR · Senior Lead Software Engineer, Python Distributed Development and AI Modernization

Role Posting Log in to save

As a Senior Lead Software Engineer- Python Distributed Development and AI Modernization within the Wealth Management Technology team, you will join an agile group focused on modernizing legacy systems. You will design and build agentic systems to ingest mainframe logic—including COBOL, JCL, DB2, and batch schedules—to produce verified, production-ready services. Your daily work involves building spec generation pipelines, developing multi-agent workflows for code translation into Kotlin/JVM, and creating automated verification infrastructure for parity testing. You will utilize Python, RAG pipelines, and AI tools like Claude Code, Copilot, and Cursor to manage LLMOps, including prompt engineering and latency optimization. The role addresses the complex challenge of migrating decades of mainframe logic into a modern, scalable platform while ensuring accuracy in financial calculations through robust orchestration layers and automated testing frameworks.

Skills

Python LLM RAG Agentic Workflows Prompt Engineering Kotlin JVM AWS EKS ECS Kubernetes PostgreSQL Kafka COBOL JCL DB2 Airflow Temporal CDC LLMOps

What you'll do

Build and operate spec generation pipelines using RAG and chunking strategies to convert mainframe logic into structured specifications.
Design and implement multi-agent systems to translate legacy COBOL and JCL code into modern Kotlin/JVM services.
Create automated test harnesses and parity testing frameworks to verify that migrated calculations match legacy outputs.
Develop and extend the target platform's calculation runtime to ensure deterministic and auditable execution.
Build and integrate ETL, change data capture (CDC), and event sourcing pipelines for end-to-end migrated workflows.
Manage LLMOps for the toolchain, including deployment, monitoring, cost management, and latency optimization of AI systems.
Develop shared libraries, prompt templates, and orchestration patterns to scale AI capabilities across multiple domains.
Drive the adoption of AI-assisted engineering practices and governance standards across the software development lifecycle.

What we're looking for

Formal training or certification on software engineering concepts and 5+ years of applied experience.
Experience in Computer Science, Computer Engineering, Mathematics, or a related technical field.
Hands-on experience building LLM-based applications including agentic architectures, RAG pipelines, prompt engineering, and evaluation frameworks.
Expert proficiency with AI-assisted development tools such as Claude Code, GitHub Copilot, and Cursor.
Strong software engineering fundamentals in distributed systems, event-driven architectures, API design, and cloud platforms (AWS/EKS/ECS).
Strong experience with Python development in production environments.
Demonstrated ability to lead the use of enterprise-authorized AI tools while ensuring security, performance, and correctness.
Experience with legacy systems (COBOL, JCL, DB2), workflow orchestration, or financial services (preferred).

Save