Sr Lead Software Engineer - Artificial Intelligence

Senior Lead Software Engineer - Artificial Intelligence role in Plano, Texas, onsite. You will design, build, and operate AI toolchains to modernize mainframe processing by translating COBOL, JCL, and DB2 logic into production-ready services. This position emphasizes collaboration with domain experts and cross-functional partners to deliver reliable, auditable software with measurable impact.

Benefits

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

Responsibilities

• Develop and operate the spec generation pipeline, enabling ingestion of COBOL source, JCL, job schedules, DB2 schemas, and SME knowledge; design chunking methods and RAG pipelines to produce structured calculation and workflow specifications validated by domain experts.
• Create agent driven workflows for translation and migration; build and iterate multi-agent systems that convert legacy logic into Kotlin/JVM code, with orchestration layers, tool usage patterns, and safeguards to ensure accuracy for financial calculations.
• Establish automated evaluation and verification infrastructure; develop test harnesses that compare migrated outputs to legacy results, implement parity testing, regression suites, and confidence scoring to guide production cutover decisions.
• Contribute to the standard calculation runtime; help build and extend the target platform for deployed migrated calculations, ensuring deterministic, immutable, auditable execution.
• Collaborate 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.
• Extend ETL and CDC pipelines for agent workflows; build event sourcing, change data capture, and data pipelines that support end to end migrated workflows, including upstream/downstream dependency mapping.
• Operate AI systems in production; own LLMOps for the toolchain including deployment, monitoring, cost management, latency optimization, token budget management, and incident response to ensure 24/7 reliability and compliance.
• Iterate rapidly and ship 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.
• Contribute to shared tooling and infrastructure; build reusable libraries, evaluation harnesses, prompt templates, and orchestration patterns that scale AI capabilities across all core processing domains.

Requirements

• At least five years of software engineering experience delivering production systems.
• Minimum of two years building LLM based applications, including agent-based architectures, RAG pipelines, prompt engineering, and evaluation frameworks.
• Strong fundamentals in distributed systems, event-driven architectures, API design, testing practices, and cloud platforms (AWS, EKS, ECS).
• Expert proficiency with AI-assisted development tools such as Claude Code, GitHub Copilot, and Cursor as part of daily workflow.
• Production experience in at least one of Kotlin/JVM, Java, Python, or Rust.
• Proven ability to operate and debug complex systems.
• Clear communicator able to 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