We are looking for a hands-on Senior / Lead AI Developer to drive enterprise application modernization using cutting-edge agentic engineering workflows. In this role, you will triage unfamiliar legacy codebases, design spec-driven modernization approaches, and author reusable AI skills and agents to safely execute framework and security upgrades.
You will lead AI-assisted development pods, guide safe tech-stack migrations across Java and .NET ecosystems, and ensure existing application architectures are preserved while upgrading to modern security and cloud-ready runtimes.
Key Responsibilities
- AI Agent & Skill Governance: Design, author, and refine reusable AI skills and agents for reverse engineering, dependency analysis, code transformation, migration, and automated verification.
- Architecture & Triage: Lead the reverse engineering of legacy and current-state enterprise applications (Java/.NET) to discover dependencies, integrations, database touchpoints, security flows, and runtime assumptions.
- Spec-Driven Modernization: Turn discovery findings into technical specifications and structured implementation plans for AI-assisted delivery pods.
- Tech-Stack & Security Upgrades: Drive framework and runtime upgrades (JDK, JBoss, application servers, dependencies) and guide the migration from legacy LDAP/authorization logic to modern token-based identity patterns (Okta, OAuth/OIDC/JWT).
- Technical Lead & Execution: Break modernization initiatives into pod-ready increments, review agent outputs and code changes, stay hands-on for high-risk components, and establish human-in-the-loop verification gates.
- Incident Management & Root Cause Analysis: Apply disciplined systems thinking to troubleshoot complex build/runtime failures and production incidents.
- Mentorship & Continuous Improvement: Mentor developers in agentic engineering, secure coding, and context engineering while capturing reusable failure modes, prompts, and verification steps.
Required Qualifications
- Experience: 7–10+ years in Software Engineering with production support/incident experience, plus 1–2 years of hands-on experience with agentic engineering and AI projects.
- AI Tooling & Agentic Engineering: Demonstrated experience building or configuring AI agents and workflows using tools such as Claude Code, Cursor, GitHub Copilot, or similar frameworks. Preference for Claude Code and custom agentic workflow development.
- Core Software Engineering: Deep expertise in Java (JDK, application servers like JBoss, Maven/Gradle) and/or .NET enterprise application modernization.
- Systems & Environment: Strong background in Linux/Red Hat and Windows server environments, understanding how OS, middleware, and database changes interact.
- Identity & Security: Understanding of legacy LDAP authentication/authorization and practical migration experience to token-based identity patterns (Okta preferred).
- Engineering Fundamentals: Strong command of APIs, SQL/databases, CI/CD pipelines, Git, debugging, observability, and secure software delivery.
- Systems Thinking: Ability to enter unfamiliar, large monolithic codebases, assess blast radius across downstream/upstream systems, and execute safe in-place upgrades without forcing unnecessary microservice decomposition.
Preferred Qualifications
- AI/LLM Stack: Proficiency in Python, modern LLM/agent frameworks, Model Context Protocol (MCP)/tool integration, prompt engineering, and RAG.
- Cloud & Platform: Experience with GCP / Vertex AI or enterprise cloud AI platforms.
- Application Security: Vulnerability remediation, software supply-chain controls, secrets management, OAuth2/OIDC, and JWT implementation.