Sr Lead Software Engineer - Artificial Intelligence

JPMorganChase is seeking a Senior Lead Software Engineer - Artificial Intelligence to design, build, and operate AI toolchains that modernize mainframe processing by translating COBOL, JCL, and DB2 logic into production-ready services. This onsite role in Plano, Texas places you at the intersection of software engineering and advanced AI, collaborating with domain experts to ensure reliable, auditable migration of critical financial workflows. The position blends hands-on development with leadership in agent-based translation, verification, and runtime evolution for complex processing domains.

Responsibilities

• Architect and maintain the specification-generation pipeline, enabling artifact ingestion of COBOL sources, JCL, job schedules, DB2 schemas, and SME knowledge; design chunking strategies and RAG pipelines to produce structured calculation and workflow specifications validated by domain experts.
• Designs and implements multi-agent workflows that translate legacy COBOL/JCL logic into target-state Kotlin/JVM code, building orchestration layers, tool-use patterns, and guardrails to ensure correctness of financial calculations.
• Establishes evaluation and verification infrastructure, including automated test harnesses that compare migrated results with legacy outputs, parity testing, regression suites, and confidence scoring to inform production cutover decisions.
• Contributes to the standard calculation runtime by shaping and extending the target platform where migrated calculations deploy, ensuring deterministic, immutable, auditable execution.
• Collaborates with domain SMEs 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 by building and integrating event sourcing, CDC, and data pipelines that map upstream and downstream dependencies for end-to-end migrated processes.
• Operates AI systems in production, owning LLMOps for deployment, monitoring, cost management, latency optimization, token budgeting, and incident response to ensure 24/7 reliability and compliance.
• Performs rapid iterative development cycles, prototyping quickly, instrumenting metrics, and making data-driven decisions about agent architectures, model selection, and prompt strategies.
• Contributes to shared tooling and infrastructure by building reusable libraries, evaluation harnesses, prompt templates, and orchestration patterns that scale AI capabilities across all four core processing domains.

Requirements

• 5+ years of software engineering experience shipping production systems
• 2+ years hands-on experience building LLM-based applications — agentic architectures, RAG pipelines, prompt engineering, and evaluation frameworks
• Strong software engineering fundamentals in 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 part of daily workflow
• Production experience with at least one of Kotlin/JVM(Java), Python, Rust
• Demonstrated ability to operate and debug complex systems
• Clear communicator who can articulate technical trade-offs to engineers and business stakeholders
• Experience with code migration

Technologies

• COBOL
• JCL
• DB2
• Kotlin
• Java
• Python
• Rust
• AWS
• EKS
• ECS
• Temporal
• Airflow
• Kafka
• PostgreSQL
• Kubernetes
• CDC
• Claude Code
• GitHub Copilot
• Cursor
• LLM

Benefits

• Comprehensive health care coverage
• On-site health and wellness centers
• Retirement savings plan
• Backup childcare
• Tuition reimbursement
• Mental health support
• Financial coaching