AI Full Stack Engineer

Varmoda is seeking an experienced AI Full-Stack Engineer to design, develop, test, and deploy an AI-enabled enterprise intake and workflow automation platform. This role will build modern front-end and back-end services, conversational AI experiences, recommendation capabilities, risk-assessment workflows, enterprise integrations, and automated delivery pipelines.

The ideal candidate will have strong full-stack development experience and practical expertise with generative AI, large language models, AI-assisted engineering, ServiceNow integration, cloud-native architecture, and accelerated MVP delivery. This individual will collaborate with product, architecture, business, security, DevOps, and quality engineering teams to deliver a secure, accessible, scalable, and production-ready solution.

Key Responsibilities

• Design, develop, test, deploy, and maintain an AI-enabled enterprise intake application and its supporting services.
• Build responsive, accessible, and user-friendly front-end components using modern JavaScript frameworks.
• Develop scalable back-end services, business logic, data-access components, and integration layers.
• Translate business requirements, user stories, and architecture specifications into maintainable production code.
• Develop reusable components, shared libraries, and common services that support future expansion.
• Apply software engineering standards covering code quality, maintainability, scalability, observability, and performance.
• Participate in peer reviews, technical design discussions, demonstrations, and release-readiness activities.
• Troubleshoot application defects, performance issues, integration failures, and environment-related problems.
• Build AI-guided workflows that help users capture business needs, objectives, success measures, constraints, and high-level requirements.
• Develop intelligent prompts, guided questions, recommendations, summaries, and next-step suggestions.
• Implement validation logic to improve the completeness, consistency, and quality of submitted information.
• Design user experiences that simplify complex intake and request-management processes.
• Connect AI-generated outputs to downstream workflow, review, and approval activities.
• Include appropriate human review for material recommendations and decisions.
• Capture user feedback and apply it to improve the accuracy and usability of AI-assisted experiences.
• Document prompt logic, workflow behavior, assumptions, limitations, and expected outcomes.
• Design and develop conversational AI experiences using enterprise-approved generative AI platforms.
• Integrate large language models with application interfaces, workflow services, APIs, and enterprise data sources.
• Apply prompt engineering, structured outputs, retrieval-augmented generation, tool use, and AI-agent patterns where appropriate.
• Develop context-aware chatbot and virtual-assistant capabilities.
• Implement output validation, error handling, fallback responses, and human escalation paths.
• Evaluate AI responses for relevance, accuracy, consistency, security, and user experience.
• Maintain clear separation between AI recommendations and authoritative business decisions.
• Monitor AI-enabled functionality and recommend improvements based on usage and performance.
• Develop recommendation capabilities that match user needs with existing software, infrastructure, services, and reusable enterprise assets.
• Design ranking and matching logic that prioritizes reuse before recommending new acquisitions or development.
• Build user interfaces that clearly explain recommendations, supporting factors, and available alternatives.
• Develop prioritization workflows based on business value, impact, urgency, risk, complexity, and implementation effort.
• Create AI-assisted risk-assessment modules supporting business, technical, security, and operational review.
• Integrate recommendations and risk findings into request-routing and approval workflows.
• Capture user feedback to improve recommendation quality and relevance.
• Maintain documentation describing recommendation rules, assumptions, data sources, and limitations.
• Develop integrations with enterprise workflow, request-management, and service-management platforms.
• Build automated workflows covering intake, classification, routing, assignment, review, approval, escalation, and closure.
• Develop APIs and data-exchange components connecting the solution with enterprise systems.
• Configure notifications, status updates, audit trails, business rules, and exception handling.
• Integrate application functionality with ServiceNow or comparable workflow platforms.
• Troubleshoot workflow, connectivity, authentication, data-mapping, and synchronization issues.
• Ensure integrations are secure, observable, maintainable, and appropriately documented.
• Support changes to workflows and integrations as operational requirements evolved
• Design, develop, document, and maintain REST and GraphQL APIs.
• Build modular services using microservices or service-oriented architecture patterns.
• Define API contracts, request and response models, validation rules, and error-handling standards.
• Implement authentication, authorization, logging, monitoring, and secure communication.
• Develop integrations with AI services, cloud resources, enterprise applications, and data platforms.
• Create automated unit, integration, contract, and regression tests for APIs and services.
• Monitor API health, reliability, latency, and failure patterns.
• Maintain API specifications and integration-support documentation.
•  
• Use approved AI coding assistants and pair-programming tools to support requirements analysis, code generation, debugging, testing, and documentation.
• Apply prompt-engineering techniques to improve the quality of AI-assisted development outputs.
• Validate all AI-generated code, tests, requirements, and documentation before use.
• Establish reusable prompts, development patterns, and review practices.
• Use AI tools to improve delivery efficiency while maintaining engineering quality, security, and accountability.
• Identify potential intellectual-property, privacy, security, and data-handling risks associated with AI-assisted development.
• Document significant AI-assisted technical decisions and resulting implementation changes.
• Share effective AI development practices with other team members through demonstrations and knowledge transfer.
• Develop automated unit, component, API, integration, regression, and end-to-end test suites.
• Create test coverage for front-end applications, back-end services, integrations, workflows, and AI-assisted capabilities.
• Incorporate automated testing into development and deployment pipelines.
• Develop repeatable test data, mocks, stubs, and service-virtualization components where appropriate.
• Validate functional behavior, security controls, error handling, accessibility, and performance.
• Investigate defects, determine root causes, and implement sustainable corrections.
• Maintain traceability between requirements, code changes, test results, defects, and releases.
• Support production validation and post-deployment stabilization.
• Design, configure, and maintain CI/CD pipelines in Azure DevOps or comparable delivery platforms.
• Automate application builds, testing, security checks, packaging, deployment, and post-release validation.
• Manage code through Git-based repositories using approved branching, review, and merging practices.
• Containerize applications and services using Docker.
• Support container orchestration and cloud-native deployment using Kubernetes.
• Deploy and support applications across AWS, Microsoft Azure, or comparable cloud environments.
• Implement environment-specific configuration, secret management, logging, monitoring, and rollback procedures.
• Troubleshoot build, pipeline, deployment, container, networking, and cloud-environment issues.
• Apply secure software development practices throughout design, development, testing, and deployment.
• Implement input validation, secure authentication, authorization, encryption, secrets management, and appropriate access controls.
• Integrate automated security testing and dependency scanning into CI/CD pipelines.
• Review source code and architecture for common application-security weaknesses.
• Collaborate with security and architecture teams to address identified risks.
• Maintain audit logs and technical evidence supporting security reviews.
• Ensure sensitive information is not inappropriately exposed to AI tools, application logs, prompts, or external services.
• Support remediation of security findings and validate implemented corrections.
• Create and maintain technical specifications, API documentation, architecture diagrams, deployment guides, and operational procedures.
• Document application components, integrations, dependencies, configuration settings, security controls, and data flows.
• Maintain developer onboarding and local-environment setup instructions.
• Produce troubleshooting guides and production-support documentation.
• Participate in solution demonstrations, architecture reviews, and stakeholder discussions.
• Deliver knowledge-transfer sessions to development, support, and administrative teams.
• Document technical decisions, known limitations, risks, and recommended future improvements.
• Contribute to transition planning and future expansion activities.

Required Qualifications

• Bachelor's degree in Computer Science, Software Engineering, Information Technology, or a related discipline.
• Equivalent relevant professional experience may be considered in place of the degree.
• Minimum five years of professional full-stack application development experience.
• Experience with a combination of modern development technologies, such as:
• JavaScript and TypeScript
• React or Angular
• Node.js
• Python
• .NET
• Java
• Experience developing REST APIs, GraphQL APIs, and microservices-based applications.
• Experience using Azure DevOps, GitHub, Git, CI/CD pipelines, and Agile delivery practices.
• Demonstrated experience delivering MVPs, prototypes, proofs of concept, or production solutions within accelerated timelines.
• Experience designing or implementing enterprise workflow, intake management, case management, request management, or service-delivery solutions.
• Experience integrating applications with ServiceNow or a comparable enterprise workflow platform.
• Experience with cloud-native application development in AWS, Microsoft Azure, or comparable cloud environments.
• Experience with Docker, Kubernetes, containerized deployment, and distributed application architectures.
• Experience implementing AI-powered user experiences, chatbot interfaces, or LLM integrations.
• Experience with AI-native engineering practices, including:
• AI-assisted development
• Prompt engineering
• Code generation
• Automated testing
• AI agents
• AI-augmented software delivery
• Experience with AI coding assistants or AI pair-programming platforms.
• Strong understanding of secure software development and DevSecOps principles.
• Experience working in Agile or rapid MVP delivery environments.
• Strong analytical, troubleshooting, documentation, and communication skills.
• Ability to communicate technical and AI concepts to both technical and nontechnical stakeholders.

Preferred Qualifications

• Experience building customer-facing intake, request-management, workflow, or self-service portals.
• Experience within ServiceNow-centered enterprise environments.
• Experience supporting government, public-sector, regulated, or similarly complex organizations.
• Experience integrating generative AI with enterprise applications and workflow platforms.
• Experience with retrieval-augmented generation, vector search, embeddings, AI agents, or conversational AI.
• Experience developing intelligent recommendation, ranking, routing, or decision-support capabilities.
• Familiarity with responsible AI, AI governance, privacy, and model-risk practices.
• Familiarity with Section 508, WCAG, or comparable digital accessibility standards.
• Experience conducting application-security testing and remediating security findings.
• Experience with monitoring, logging, observability, and performance optimization.
• Experience contributing to architecture documentation and technical roadmaps.
• Experience supporting pilot-to-production transition and operational readiness.

Required Certification

Candidates should possess at least one relevant professional certification in an applicable area, such as:

• Cloud computing
• DevOps or DevSecOps
• Agile or Scrum
• AWS
• Microsoft Azure
• Google Cloud
• ServiceNow
• Kubernetes
  
  Preferred Certifications
• Microsoft Certified: Azure Developer Associate
• Microsoft Certified: Azure AI Engineer Associate
• Microsoft Certified: DevOps Engineer Expert
• AWS Certified Developer
• AWS Certified Solutions Architect
• Google Cloud Professional Cloud Developer
• ServiceNow Certified Application Developer
• ServiceNow Certified Implementation Specialist
• Certified Kubernetes Application Developer
• Certified Scrum Developer or Certified ScrumMaster
• Relevant AI engineering or secure-development certification