Designs and iterates on multi-agent workflows that analyze legacy logic and translate it into target-state services, applying orchestration, tool integrations, and guardrails to support accurate, production-ready outcomes.
Builds evaluation and verification infrastructure—including automated test harnesses, parity tests, regression suites, and confidence scoring—to assess AI-generated specifications and code and inform production-readiness decisions.
Partners with domain subject-matter experts to validate AI-generated specifications and code, refine prompts and agent workflows, and identify and close knowledge gaps in source artifacts and specifications.
Integrates AI-enabled workflows with data pipelines, event sourcing, and change-data-capture processes; contributes reusable tooling and runtime capabilities that support reliable, auditable execution.
Develops secure, high-quality production code, and reviews, debugs, and troubleshoots code and systems—including AI-generated outputs—to meet engineering and operational standards.
Owns LLMOps for the production toolchain, including deployment, monitoring, cost and token-budget management, latency optimization, and incident response; identifies opportunities to automate recurring remediation and improve system stability.
Required qualifications, capabilities, and skills
Formal training or certification on software engineering concepts and 5+ years applied experience
Demonstrated experience leading effective use of approved AI-assisted software development tools (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 engineers on safe, compliant adoption within delivery practices
Hands-on experience building production LLM-based applications, including agentic architectures, RAG pipelines, prompt engineering, and evaluation frameworks.
Experience applying AI to ingest, analyze, or transform complex artifacts or data into structured, validated outputs, and to build agent workflows with orchestration, tool use, and output controls.
Strong software engineering fundamentals in distributed systems, event-driven architectures, API design, and testing, with experience using AWS cloud platforms such as EKS or ECS.
Proficiency in at least one programming language, such as Java/JVM or Python, with experience developing and operating production applications.
Expert daily proficiency with AI-assisted development tools such as Claude Code, GitHub Copilot, or Cursor; demonstrated ability to review, debug, and validate code produced with these tools.
Proficient across the Software Development Life Cycle, including agile delivery and CI/CD, with practical cloud-native experience and an ability to communicate technical trade-offs to engineering teams and business stakeholders.
Preferred qualifications, capabilities, and skills
Experience using AI or agentic workflows to analyze or modernize legacy systems, including mainframe technologies such as COBOL, JCL, or DB2, or to support large-scale migration programs.
Familiarity with workflow orchestration tools such as Temporal or Airflow.
Familiarity with event-sourcing and change-data-capture patterns, and experience with Kafka.
Experience with PostgreSQL and container orchestration platforms such as Kubernetes or EKS.
Background in financial services, such as retirement, wealth management, brokerage, or capital-markets processing.
Experience building AI-enabled code analysis, translation, or verification tooling; a master’s degree in Computer Science or equivalent experience.