Agentic AI Engineer

• Job Title: Senior/Lead AI Developer (Agentic Engineer)
• Contract Duration: 6 Months (Projected: 11/25/2026 – 04/16/2027)
• Work Schedule: Full-Time (40 hours/week), Monday – Friday, 9:00 AM – 5:00 PM CST
• Location & Remote Policy: 100% Remote (Anywhere in the US, must work CST hours). Reference Office Location: Chicago, IL 60606
• Work Authorization:Education & Experience: Bachelor’s Degree; 7–10+ years of IT/Software Engineering experience (1–2 years in agentic engineering/AI projects)
• Interview Process:
1. Internal Screening: 30–60 minute video interview via Google Meet with the Technical Director.
2. Client Interview: 30–60 minute video interview via Microsoft Teams with the client.

Project Overview & Role Summary

We are shifting our strategy from massive, slow application re-architectures to a highly targeted, AI-driven platform roadmap to stay ahead of rapidly scaling security threats. We are building internal AI agents to automate the modernization and security upgrades of our legacy enterprise applications—engineering these agents to complete 90% of the upgrade work autonomously, leaving the remaining 10% for human verification and validation.

We are looking for a Senior/Lead AI Developer (Agentic Engineer) with hands-on technical lead experience to triage unfamiliar enterprise applications, design modernization approaches, build and evolve reusable AI skills/agents, and guide small development pods through safe technology-stack and security upgrades while preserving the applications' intended architecture and behavior.

The Technical Scope (Two Primary Tracks):

• Track 1: Infrastructure & Core Tech Upgrades: Migrating legacy applications running on older Linux platforms and older Java runtimes (e.g., upgrading from JDK 17 to JDK 25) by building AI agents that scan legacy apps, generate technical specifications, and automatically execute dependency-by-dependency upgrades.
• Track 2: Security & Identity Modernization: Transitioning applications from legacy security/authentication models (LDAP/ISD) to modern Okta integration, evaluating applications on a case-by-case basis to determine stack vs. security upgrade needs.

Ideal Candidate Profile:

• Systems Thinkers: Must understand how massive enterprise systems interconnect and immediately recognize downstream impacts on connected systems when upgrading databases or servers.
• "Fixers," Not "Finders": We need hands-on engineers who build automated solutions to remediate vulnerabilities, not auditors who just identify them.
• Battle-Scarred Veterans: Candidates need real-world experience navigating complex, high-stakes system failures (P1 incidents) rather than isolated coding experience.

Duties & Responsibilities

• Lead reverse engineering of legacy and current-state applications using AI agents/skills to discover architecture, dependencies, integrations, database touchpoints, security flows, runtime assumptions, and deployment characteristics.
• Turn reverse-engineered findings into clear technical specifications and spec-driven implementation plans that can be executed by AI-assisted delivery pods.
• Design, author, refine, and govern reusable skills and agents for reverse engineering, dependency analysis, forward engineering, code modification, migration, remediation, and verification.
• Drive modernization of Java and .NET applications, including runtime/framework upgrades, dependency/JAR/package upgrades, application-server compatibility, and operating-system/infrastructure changes.
• Lead security modernization patterns, including identifying LDAP/legacy authorization logic and guiding migration to token-based identity and access patterns using Okta, OAuth/OIDC/JWT concepts as appropriate.
• Preserve existing application architecture where required, focusing on making applications run safely on target infrastructure rather than unnecessarily decomposing or re-platforming them.
• Assess blast radius across databases, interfaces, shared libraries, batch processes, downstream/upstream systems, configuration, and deployment pipelines before changes are executed.
• Break modernization work into pod-ready increments, assign work to developers, review agent outputs and code changes, and remain hands-on for complex or high-risk components.
• Continuously improve agent effectiveness across applications by capturing reusable patterns, failure modes, context requirements, prompts/instructions, and verification steps.
• Partner with AI Test Leads, architects, security, infrastructure, and application stakeholders to define acceptance criteria, quality gates, rollback considerations, and production readiness.
• Lead technical troubleshooting and root-cause analysis for complex failures and production-like issues; bring strong P1 incident experience and disciplined systems thinking.
• Mentor developers in agentic engineering, spec-driven development, secure coding, code review, dependency management, and human-in-the-loop verification.

Required Skills

• 7–10 years of IT experience working as a Software Engineer with production/P1 incident experience, plus 1–2 years working with agentic engineering and AI projects.
• Demonstrated hands-on experience building or materially configuring AI agents/skills for software-engineering workflows (e.g., Claude Code, Cursor, GitHub Copilot, or comparable agentic tooling). Preferred usage of Claude Code and creation of Agentic Coding workflows.
• Strong systems thinking ability to enter an unfamiliar codebase and determine where to inspect code, configuration, dependencies, data stores, integrations, security controls, runtime behavior, and operational risks.
• Deep software engineering experience in Java and/or .NET, with a strong preference for enterprise Java modernization involving JDK, JBoss/application servers, deployments, Maven/Gradle, and dependency remediation.
• Working knowledge of Linux/Red Hat and Windows application environments and how runtime, OS, middleware, database, and library upgrades interact.
• Conceptual and practical understanding of LDAP-based authentication/authorization and migration to modern token-based identity patterns (Okta strongly preferred).
• Strong API, database, SQL, integration, CI/CD, Git, debugging, logging, observability, and secure software-delivery fundamentals.
• Experience with spec-driven development, technical design documentation, code review, automated testing, and production deployment/support.
• Ability to distinguish AI-generated suggestions from verified engineering outcomes and establish explicit human approval/verification points.

Preferred Skills

• Python and modern LLM/agent frameworks; MCP/tool integration; prompt/context engineering; RAG where relevant.
• Google Cloud Platform/Vertex AI or other enterprise cloud AI platforms.
• Application security, vulnerability remediation, software supply-chain controls, secrets management, OAuth/OIDC, and JWT.
• Experience leading modernization of large monolithic applications without forcing unnecessary microservice decomposition.

Recruiter Screening Questions

1. "Tell me about a time you had to modernize a legacy application. How did you map out the downstream impacts before making changes?" (Listen for systems thinking and architectural awareness, not just code-level changes).
2. "How many P1 (Priority 1) incidents have you been involved in during your career, and what did they teach you about system design?" (Listen for battle scars and lessons learned).
3. "If I asked you to automate a massive JDK upgrade across dozens of legacy applications today, how would you approach building an AI agent to do 90% of the work?" (Listen for an understanding of agentic engineering, automation, and prompt/skill design).