Application / Agentic AI Engineer

NextGen is seeking a highly motivated and technically skilled Application/Agentic AI Engineer to support the integration, and deployment of modern AI-enabled applications and agentic AI capabilities in support of mission objectives using ReadiChat.

ReadiChat is a mission-focused, agentic AI platform designed to help organizations build, deploy, govern, and scale specialized AI agents for operational workflows. It combines AI agents, workflow orchestration, grounded knowledge, testing frameworks, and enterprise controls into a single collaborative workspace.

The selected candidate will work across software engineering, AI/ML integration, workflow orchestration, and operational problem-solving to develop intelligent systems that improve decision-making, automation, and user interaction in complex environments. This role requires a blend of software engineering expertise, AI integration experience, systems thinking, and the ability to collaborate directly with operational users, engineers, and program stakeholders to translate mission requirements into scalable AI-enabled solutions.

Responsibilities

• Partner with customer SMEs and operational stakeholders to translate mission workflows and operational requirements into agentic AI solutions, including intelligent agents, workflow specialists, guardrails, tools, and validation frameworks.
• Design, develop, and maintain agent definitions and configurations, including objectives, behavioral instructions, input/output contracts, safety policies, operational constraints, and tool utilization rules.
• Develop workflow-specific AI specialists and reusable agent patterns to support operational and enterprise use cases while maintaining clear functional boundaries and scalable architectures.
• Build and maintain comprehensive AI testing and evaluation suites, including gold-standard input/output validation, adversarial testing, guardrail validation, scope-boundary testing, tool-use validation, regression testing, and multi-turn conversational testing.
• Analyze failed, degraded, or stale agent test results to identify performance gaps, tune agent behavior, improve reliability, and document updates across agent versions and releases.
• Integrate AI agents, orchestration workflows, APIs, and supporting services into existing application and operational environments using modern software engineering and DevSecOps practices.
• Support the deployment, sustainment, troubleshooting, and optimization of AI-enabled applications and agentic workflows across cloud, edge, and hybrid environments.
• Train and mentor customer agent creators on Agent Builder workflows, publishing processes, testing methodologies, maintenance procedures, and operational best practices.
• Develop reusable templates, workflow examples, implementation guides, and best-practice documentation to enable scalable and consistent customer development of agentic AI solutions.
• Collaborate with cross-functional engineering, operations, cybersecurity, and product teams to ensure AI-enabled capabilities align with mission objectives, security requirements, and operational constraints.
• Contribute to continuous improvement efforts for AI-enabled applications, orchestration frameworks, testing methodologies, and software delivery pipelines.

Required Qualifications

• Bachelor’s degree in Computer Science, Software Engineering, Data Science, Information Systems, or related technical discipline.
• 3+ years of experience in software engineering, application development, or AI/ML integration.
• Experience developing applications using Python, JavaScript, TypeScript, Java, or similar modern programming languages.
• Experience integrating APIs, microservices, and data services into enterprise or operational applications.
• Familiarity with Large Language Models (LLMs), prompt engineering, AI orchestration frameworks, or agentic AI concepts.
• Experience with cloud-native technologies and containerized environments such as Docker and Kubernetes.
• Understanding software development lifecycle (SDLC), DevSecOps, and CI/CD methodologies.
• Experience with Git-based version control and collaborative development workflows.
• Strong analytical, troubleshooting, and problem-solving skills.
• Ability to communicate technical concepts effectively to both technical and non-technical stakeholders.
• Active Security Clearance is required

Desired Qualifications

• Experience with AI orchestration frameworks such as LangChain, LangGraph, Semantic Kernel, CrewAI, AutoGen, or similar technologies.
• Familiarity with AI model deployment, inference optimization, and scalable AI architecture.
• Experience supporting government, defense, intelligence, or mission-focused environments.
• Experience with AWS, Azure, or Google Cloud AI services.
• Familiarity with cybersecurity best practices and secure software development.
• Experience developing operational workflows using AI agents, automation pipelines, or decision-support systems.