Agentic AI Systems Engineer

Corner Alliance•Washington, DC

About The Position

This role is contingent upon award. Corner Alliance is a dynamic, growing consulting firm that devotes itself to providing an enriching employee experience while working in meaningful ways to create results for the government. We are currently seeking an Agentic AI Systems Engineer to join our team and fully embrace our commitment to deliver, grow and thrive. This role will support a client effort to develop agentic artificial intelligence capabilities. The solution will help improve efficiency and compliance while maintaining human control, accessibility, traceability, and alignment with best practices. As an Agentic AI Systems Engineer, you will help design, develop, integrate, test, and refine an AI-enabled interface. You will bring technical expertise across agentic AI, software engineering, data architecture, large language model integration, application programming interfaces, cloud hosting, structured data workflows, and secure system design. You will work with project leadership, subject matter experts, client stakeholders, and technical partners to build a secure, human-in-the-loop AI capability that supports notification drafting and validation from incident reviews and emerging research.

Requirements

Bachelor's degree or higher in computer science, data science, engineering, information systems, artificial intelligence, cybersecurity, or related field.
Six or more years of experience in software engineering, data architecture, AI system development, cloud application development, or related technical roles.
Demonstrated experience designing, developing, implementing, and testing scalable software applications, data pipelines, APIs, or AI-enabled systems.
Proficiency with Python, JavaScript, and SQL (Structured Query Language); working experience with at least one major cloud platform (AWS, Azure, or Google Cloud Platform), including secure cloud environments.
Experience developing or integrating REST APIs, structured data services, and front-end components such as JavaScript/HTML widgets or embedded panels.
Demonstrated experience with AI/ML or LLM-enabled solutions across at least three of the following, with prompt engineering and either retrieval-augmented generation or agentic workflows required: prompt engineering, model orchestration, retrieval-augmented generation, structured outputs, evaluation methods, agentic workflows.
Experience designing data models, mapping data lineage, managing business rules, and translating stakeholder needs into technical requirements.
Working knowledge of containerization (e.g., Docker), version control (Git), and continuous integration/continuous deployment (CI/CD) practices.
Ability to document technical designs, workflows, requirements, testing results, and user-facing guidance clearly.
Strong analytical, problem-solving, and communication skills.
Strong attention to detail and commitment to quality assurance.
Ability to collaborate with clients, subject matter experts, developers, and nontechnical stakeholders in a professional environment.
U.S. citizenship and ability to obtain and maintain a federal Public Trust or suitability determination as required by the client.

Nice To Haves

Experience supporting public safety communications, emergency management, alerting and warning systems, or related mission-critical technology efforts.
Experience with accessibility, Section 508, access and functional needs, multilingual content workflows, translation technology, or plain-language communication.
Experience applying AI risk management frameworks such as the NIST AI RMF (National Institute of Standards and Technology AI Risk Management Framework), security controls, audit logging, data minimization, or human-in-the-loop governance.
Familiarity with federal AI policy guidance such as OMB (Office of Management and Budget) M-24-10 or successor memoranda.
Experience with FedRAMP (Federal Risk and Authorization Management Program)-authorized cloud environments.
Experience with data platforms such as Databricks, Snowflake, data lakes, or data warehouses.
Experience with automated testing frameworks for AI/ML (machine learning) systems.
Experience developing AI solutions for high-consequence, regulated, public sector, emergency response, or mission-critical environments.
Don’t think you have everything for this role but are still very interested? Please don’t hold back from applying because you may not have it all. You can learn and grow with us. We're looking for someone who is coachable, unflappable in navigating challenges, resourceful in learning new skills, innovative in challenging the status quo, excellent in writing, analytical in thinking, skilled in prioritization, and a rapport builder with clients and colleagues.

Responsibilities

Lead the design and development of an agentic AI system that helps draft clear, concise, accessible, and actionable notifications, while preserving human approval for all transmission decisions.
Architect and implement AI agents that perform drafting, template management, validation, readability checks, geo-targeted language adaptation, translation support, and incorporation of operator feedback over time.
Apply LLM (large language model), RAG (retrieval-augmented generation), model orchestration, prompt engineering, structured output, and agentic workflow techniques to enable reliable AI-assisted notification generation.
Translate accessibility, public safety communications, and client requirements into technical features, user stories, data flows, and system architecture.
Design and develop REST (representational state transfer) API (application programming interface) endpoints and integration patterns that allow the AI capability to operate within existing environments — including draft message generation, message validation, geo-language suggestions, readability checks, and template retrieval.
Develop front-end integration components, including lightweight JavaScript/HTML widgets or side panels that surface AI assistance within existing operator workflows.
Architect structured data workflows that ingest fields, geographic polygons, hazard types, constraints, templates, validation rules, historical data, and operator inputs.
Develop deterministic validation logic that checks required fields, character limits, segmentation, language tags, accessibility metadata, and alignment with applicable standards.
Design evaluation frameworks and test harnesses to assess quality, factuality, accessibility, consistency, regulatory compliance, and operational usefulness across model versions and prompt revisions.
Implement secure, compliant cloud hosting practices, including deployment, data minimization, audit logging, role-based access control, and privacy-conscious retention.
Collaborate with subject matter experts (SMEs) to incorporate social science research, design guidance, historical data, best practices, templates, and lexicons into system behavior.
Document system architecture, data models, workflows, APIs, security assumptions, validation logic, and operational procedures; participate in stakeholder demonstrations, technical reviews, dry runs, user feedback sessions, and iterative agile sprints.
Carry out our Commitments to Deliver, Grow, and Thrive.