Lead Full Stack AI Solution Developer- 100% remote

Job Summary: ** This role will serve as a lead full stack engineering developer responsible for developing resiliency-focused AI-enabled capabilities into operational, supportable, and sustainable enterprise solutions. The selected candidate will lead hands-on development across the full application stack, including user interface development, backend service development, data engineering, database design, containerized deployment, CI/CD automation, and operational troubleshooting. The ideal candidate is an experienced full stack developer who has built, deployed, maintained, and sustained production applications. This role requires more than the ability to generate code; the selected candidate must understand how the solution works, be able to explain design decisions, troubleshoot issues across the stack, review AI-assisted code critically, and ensure the team retains technical ownership of the system. The responsibilities of this position include, but are not limited to: Lead full stack development of AI-enabled solutions from prototype/proof-of-concept maturity into operational capability. Develop, maintain, and troubleshoot frontend applications and backend services. Support development and sustainment of Model Context Protocol (MCP) services. Support integration of AI/LLM capabilities, agent workflows, and model/tool interactions into enterprise applications. Design and implement database and data engineering capabilities, including selection of appropriate database technologies, schema/data model design, data access patterns, and integration with application services. Develop and maintain containerized applications using Docker and deploy solutions to OpenShift/Kubernetes environments. Build and maintain GitLab repositories, branching strategies, merge request practices, and GitLab CI/CD pipelines that automate build, test, containerization, and deployment activities. Automate deployment to OpenShift using Helm charts and related deployment/configuration management practices. Integrate applications with enterprise authentication and authorization patterns Identify and troubleshoot application, container, deployment, integration, authentication, database, and performance issues across the full stack. Develop and maintain technical documentation, operational procedures, troubleshooting guides, and sustainment handoff materials. Provide technical leadership to other developers and collaborate with product owners, architects, platform teams, cybersecurity, operations, and mission stakeholders. Requirements: Experience leading full stack software development efforts and/or serving as a senior technical contributor on production software applications. Hands-on experience developing and sustaining frontend and backend services. Experience using GitLab for source control, code review, merge requests, and team-based software development. Experience deploying, operating, or troubleshooting applications in OpenShift or Kubernetes environments. Experience with modern software delivery practices, including automated build, test, packaging, containerization, and deployment. Experience with data engineering concepts, data modeling, data persistence, and application/database integration. Knowledge of OAuth 2.0 or similar authentication and authorization patterns. Ability to review and understand code developed by others, including AI-assisted code, and determine whether it is correct, maintainable, secure, and operationally supportable. Demonstrated ability to provide technical leadership, mentor developers, communicate design decisions, and collaborate with cross-functional teams. Desired Skills: Experience with observability, logging, monitoring, and troubleshooting tools. Familiarity with ServiceNow or similar IT service management platforms. Experience developing, integrating, or sustaining AI-enabled applications, LLM-based solutions, agentic workflows, or AI-assisted automation capabilities. Familiarity with LangGraph or similar Python-based agentic frameworks. Familiarity with Model Context Protocol (MCP), tool calling, skills, agents, prompts, context windows, token usage, and LLM application design considerations. Highly adaptive to priority changes, able to work independently, and able to balance rapid development with long-term maintainability and sustainment. Familiarity with AI/ML infrastructure, responsible AI considerations, and practical limitations of LLM-based systems