TixelJobs
K
Kyndrylvia muse

Agentic AI Engineer – Mainframe Modernization

KA, INPosted 3d ago
ML EngineerMid LevelFull-time

About the Role

**Who We Are**

At Kyndryl, we run and reimagine the mission\-critical technology systems that drive advantage for the world’s leading businesses. We are at the heart of progress; with proven expertise and a continuous flow of AI\-powered insight, enabling smarter decisions, faster innovation, and a lasting competitive edge. For our people—Kyndryls—that means doing purposeful work that powers human progress. Join us and experience a flexible, supportive environment where your well\-being is prioritized and your potential can thrive.





**The Role**

**Your Role:**



You will be an AI \& Mainframe Modernization Engineer deploying and scaling KAF and Agentic AI capabilities to accelerate legacy enterprise transformations. Working alongside mainframe SMEs, architects, and cloud teams, you will build code\-aware AI workflows, automate reverse engineering and refactoring, and enforce validation guardrails to deliver production\-ready modernization outcomes.





**What You Will Do:**



* **Deploy \& Optimize AI Workflows:** Configure and scale KAF, Agentic AI workflows, RAG pipelines, and code\-aware agents to accelerate legacy discovery, inventory analysis, and automated reverse engineering across COBOL, PL/I, JCL, CICS, IMS, and DB2\.
* **Drive Code Transformation:** Extract business rules, dependency maps, and architecture artifacts to support code refactoring and cloud migration.
* **Integrate into Enterprise Pipelines:** Embed AI automation directly into existing enterprise tools, code repositories, and CI/CD development pipelines.
* **Enforce Governance \& Quality:** Establish evaluation frameworks, guardrails, and Human\-in\-the\-Loop (HITL) validation workflows to ensure output accuracy and enterprise security compliance.
* **Scale \& Mentor:** Continuously refine prompt and orchestration frameworks, build reusable AI accelerators, and mentor cross\-functional modernization teams on AI\-assisted delivery.

**Required Qualifications:**



* Experience deploying, configuring, integrating, and optimizing enterprise Agentic AI capabilities, orchestration pipelines, custom workflows, and prompt libraries.
* Strong AI engineering expertise in designing code\-aware AI agents, Retrieval\-Augmented Generation (RAG) pipelines, vector\-based knowledge systems, prompt engineering, and context engineering.
* Hands\-on mainframe modernization background covering legacy application discovery, inventory analysis, and automated reverse engineering across COBOL, PL/I, JCL, CICS, IMS, DB2, and related technologies.
* Demonstrated ability to generate application documentation, business rules extraction, dependency maps, and architecture artifacts, converting AI outputs into implementation\-ready engineering deliverables.
* Practical experience supporting code transformation, refactoring, and migration activities while automating repetitive tasks across analysis, mapping, testing, and documentation generation.
* Proven ability to integrate AI solutions with enterprise tools, repositories, and development pipelines while monitoring and improving performance, accuracy, reliability, and scalability.
* Strong background in AI quality, validation, and governance—including defining evaluation frameworks, validation mechanisms, guardrails, Human\-in\-the\-Loop (HITL) workflows, and enterprise security compliance.
Proven collaboration skills with Mainframe SMEs, Architects, Cloud Engineers, and Transformation Leads, including mentoring teams on AI\-assisted delivery best practices.
*

**Preferred Qualifications:**



* Direct experience working with KAF (Kyndryl Agentic Framework) and contributing to reusable AI assets and modernization accelerators across multiple programs.
* Deep expertise in validating AI\-generated code, test assets, migration outputs, and documentation within regulated or security\-sensitive enterprise environments.
* Track record of identifying recurring modernization challenges and converting them into r
Share