AI Modernization Senior Lead Software Engineer

JPMorganChase•Jersey City, NJ

About The Position

Be an integral part of an agile team that's constantly pushing the envelope to enhance, build, and deliver top-notch technology products. As an AI Modernization Senior Lead Software Engineer at JPMorganChase within the Consumer and Community Bank- Wealth Management Technology, 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. In this role you will design, build, and ship the agentic systems that ingest decades of mainframe logic and produce verified, production-ready modern services. You work directly alongside domain SMEs to turn legacy COBOL, JCL, DB2, and batch schedules into structured specifications — then drive those specs through agent-accelerated delivery into the target platform. You are a builder first: comfortable architecting multi-agent orchestration one day and debugging a prompt chain against production edge cases the next. You have deep proficiency extending and operating coding agents (Claude Code, Codex, Copilot), and you bring the engineering rigor to make AI outputs reliable at enterprise scale. You thrive on hard problems, move fast, and care deeply about shipping software that works.

Requirements

Formal training or certification on software engineering concepts and 5+ years applied experience
Hands-on experience building LLM-based applications — agentic architectures, RAG pipelines, prompt engineering, and evaluation frameworks
Strong software engineering fundamentals: distributed systems, event-driven architectures, API design, testing practices, and cloud platforms (AWS/EKS/ECS)
Expert proficiency with AI-assisted development tools (Claude Code, GitHub Copilot, Cursor) as core daily workflow
Strong experience with Python development in production environments
Demonstrated ability to operate and debug complex systems — you own what you ship
Clear communicator who can articulate technical trade-offs to both engineers and business stakeholders
Demonstrated experience leading effective use of enterprise-authorized AI-assisted software development tools within the work environment (e.g., for coding, code review, test acceleration, troubleshooting) with the ability to set team expectations for validating AI outputs for correctness, performance, and security
Strong understanding of responsible AI use in engineering workflows, including data sensitivity considerations, secure handling of inputs/outputs, and adherence to resiliency and security expectations; experience coaching senior engineers/leads on compliant usage patterns and controls.
Experience in Computer Science, Computer Engineering, Mathematics, or a related technical field

Nice To Haves

Experience with legacy systems, mainframe technologies (COBOL, JCL, DB2), or large-scale migration programs
Familiarity with workflow orchestration (Temporal, Airflow) and event sourcing / CDC patterns and experience building code analysis, translation, or verification tooling
Experience with Kafka, PostgreSQL, and container orchestration (Kubernetes/EKS)
Background in financial services — wealth management, brokerage, or capital markets processing

Responsibilities

Builds and operates the spec generation pipeline — Implement artifact ingestion (COBOL source, JCL, job schedules, DB2 schemas, SME-captured knowledge), chunking strategies, and RAG pipelines that produce structured calculation and workflow specifications validated by domain experts.
Develops agentic workflows for code translation and migration — Design, implement, and iterate on multi-agent systems that translate legacy logic into target-state code (Kotlin/JVM). Build orchestration layers, tool-use patterns, and guardrails that ensure output correctness for financial calculations.
Builds evaluation and verification infrastructure — Create automated test harnesses that compare migrated calculation outputs against legacy results. Implement parity testing frameworks, regression suites, and confidence scoring to gate production cutover decisions.
Contributes to the standard calculation runtime — Help build and extend the target platform that migrated calculations deploy into. Ensure the runtime supports deterministic, immutable, auditable execution.
Partners with domain SMEs — Embed with mainframe subject-matter experts across Credit, Money Market & Mutual Funds, Statements & Tax, and IBOR to validate agent outputs, refine prompt strategies, and close knowledge gaps in specifications.
Extends ETL and CDC pipelines for agent workflows — Build and integrate event sourcing, CDC (change data capture), and data pipelines that support end-to-end migrated workflows, including upstream/downstream dependency mapping.
Operates AI systems in production — Own LLMOps for the toolchain: deployment, monitoring, cost management, latency optimization, token budget management, and incident response. Ensure reliability and compliance for 24/7 operation.
Iterates rapidly and ships continuously — Work in tight build-measure-learn cycles. Prototype quickly, instrument everything, and make data-driven decisions about agent architectures, model selection, and prompt strategies.
Contributes to shared tooling and infrastructure — Build reusable libraries, evaluation harnesses, prompt templates, and orchestration patterns that scale AI capabilities across all four core processing domains.
Drives adoption and governance of approved AI-assisted engineering practices across teams to improve code quality, delivery speed, and operational outcomes (e.g., AI-assisted code review/refactoring, test acceleration, release readiness, incident/root-cause analysis), while establishing measurable validation standards (secure coding, peer review, automated testing) and promoting reuse of proven patterns and automation within the SDLC/TLM toolchain.
Applies knowledge of tools within the Software Development Life Cycle toolchain, including approved AI-assisted development and automation capabilities, to improve the value realized by automation at scale.