Agentic Solutions Architect

Job Description

Job Description

Description:

About Us:

eSimplicity is a modern digital services company that partners with government agencies to improve the lives and protect the well-being of all Americans, from veterans and service members to children, families, and seniors. Our engineers, designers, and strategists cut through complexity to create intuitive products and services that equip federal agencies with solutions to courageously transform today for a better tomorrow

Purpose and Scope:

We are seeking a passionate Agentic Solutions Architect experienced in designing and delivering complex LLM-based AI/ML systems and multi-agent solutions, with a strong emphasis on agent orchestration, governance, scalability, and efficiency.

This customer solution Subject Matter Expert (SME) will act as an enthusiastic advocate driven to help our teams and customers deliver better and faster business outcomes through the strategic application of agentic AI.

Responsibilities

• Identify and own entire technical solution requirements in the development of enterprise-wide agentic AI and LLM-driven information systems.
• Create specific technical designs, model and tooling selections (LLMs, agent frameworks, vector stores, orchestration platforms), and end-to-end agentic architectures.
• Provide subject matter expertise on LLMs, agent frameworks (e.g., Agentbricks, AgentCore, Agentforce, LangGraph, CrewAI, AutoGen, Semantic Kernel), and orchestration platforms, leading the decision-making process to identify the best structural options.
• Serve as the core technical owner of complex agentic AI implementations, driving continuous reengineering and refactoring efforts to ensure the simplest, most elegant, and efficient systems possible to accomplish business needs.
• Ensure strategic alignment of agentic and AI/ML architectures to support business growth and evolution, staying at the forefront of emerging models, agent patterns, and protocols.
• Establish and maintain comprehensive governance frameworks spanning the entire agentic AI lifecycle: prompt and policy management, agent guardrails, risk assessment, bias/fairness and hallucination monitoring, audit logging, transparency, immutability, and regulatory compliance.
• Contribute to the strategic development and management of agentic AI product roadmaps, backlogs, and measurable success criteria, authoring detailed user stories for agent capabilities and human-in-the-loop workflows.
• Enhance and maintain a scalable systems/solutions architecture for a multi-agent platform that supports continued growth, innovation, and modernization of AI capabilities across an expanding ecosystem of internal and external stakeholders.
• Develop and design complex agentic solutions through cross-functional collaboration across a variety of LLM, RAG, tool-use, and cloud-native AI architectures.
• Develop solutions utilizing Agile frameworks and modern automation strategies, including LLMOps, MLOps, DevSecOps, and agentic hyper-automation methodologies.
• Spearhead continuous innovation and programmatic improvements, acting as a champion for the project's cultural ethos and advocating for Consumer-Driven Engineering.
• Act as a hands-on Agentic Solutions Architect and the ultimate tier-SME for assigned functional areas across LLM, agent, and AI/ML solution engineering.
• Collaborate closely with the program Chief Architect, augmenting roles as needed, including serving as Deputy Chief Architect for the program with respect to agentic AI implementation and enterprise adoption.
• Lead, manage, and mentor individuals and engineering teams, providing direct people-management support through coaching, professional development, regular 1:1 meetings, and fostering structured career growth.
• Install, configure, and administer enterprise-grade agentic platforms—specifically focusing on agent orchestration, tool/function calling, Model Context Protocol (MCP), Agent-to-Agent (A2A) networks, model gateways, and governance—ensuring top-tier reliability, performance, and scalability.
• Create seamless integrations with CI/CD pipelines, identity/access controls, APIs, repositories, and centralized monitoring systems.
• Deploy hands-on enterprise deployment models that guarantee data and AI security across PII/PHI boundaries, agent identities, robust access controls, and authorization mechanisms.
• Train engineering teams and customer end-users, developing tailored onboarding and adoption materials, and leading practical workshops to drive rapid utilization and trust in agentic AI workflows.
• Build consensus and align diverse stakeholder groups including data science, DevSecOps, compliance, legal, and business units around secure agentic AI capabilities and platform value.
• Perform other duties as assigned.

Required Qualifications

• A bachelor’s degree in computer science, Information Systems, Engineering, Mathematics, or a related scientific or technical discipline. (In lieu of a degree, an equivalent combination of education and experience will be considered).
• Minimum of 10 years leading the system architecture of complex, cloud-based enterprise systems, including data pipelines, analytics, and enterprise AI/ML workloads.
• Strong fundamental experience in software engineering, demonstrating standard implementation of engineering best practices and iterative/continuous delivery principles.
• 6 years of hands-on software development experience designing solutions on complex cloud and data architectures (e.g., Databricks, Hadoop, EMR, Spark, Redshift).
• At least 2 years of hands-on production experience designing, building, or deploying complex LLM-based AI/ML solutions (including RAG, fine-tuning, prompt engineering, systematic evaluation, and model gateways).
• At least 1 year of hands-on production experience designing, building, or deploying agent-based solutions (single-agent or multi-agent), explicitly involving agent orchestration, tool/function calling, memory architectures, and human-in-the-loop patterns using frameworks such as Agentbricks, AgentCore, Agentforce, LangGraph, CrewAI, AutoGen, or Semantic Kernel.
• Proven experience with data preparation workflows tailored for AI/ML and agentic systems, including data augmentation, data quality analysis, profiling, embeddings/vector data creation, and developing enterprise AI data strategy recommendations.
• Proven experience designing highly secure AI and data solutions handling Protected Health Information (PHI) and Personally Identifiable Information (PII), alongside associated governance, access controls, and detailed auditability.
• Demonstrated experience collaborating with customers and organizational stakeholders to present solutions to user communities and successfully drive user adoption.
• Experience designing cost-optimized, cloud-scalable AI/ML and agentic solutions, including deep familiarity with LLM cost management and latency tuning.
• Demonstrable experience establishing alignment and consensus across multiple interested or affected corporate stakeholder groups.
• Experience working smoothly within an Agile or SAFe (Scaled Agile Framework) environment.
• Excellent verbal, written, and presentational communication skills.
• Ability duly to obtain and maintain a Public Trust clearance. Must reside in the United States.

Desired Qualifications

• Relevant industry experience within Healthcare vertical sectors (Medicare, Medicaid, commercial health insurance) or direct technical delivery experience with federal government agencies such as the Centers for Medicare & Medicaid Services (CMS).
• Data and AI platform certifications (e.g., Databricks, AWS Bedrock, Azure AI), foundational cloud certifications (e.g., AWS), or advanced coding certifications (e.g., Python).
• Certifications or advanced training involving designing and implementing LLM, RAG, and agentic AI architectures (e.g., AWS Generative AI, Azure AI Engineer, NVIDIA, LangChain).
• Demonstrated history of successful, applied agentic AI outcomes that achieved meaningful and measurable improvements in enterprise productivity, organizational decision quality, or overall mission impact (such as reduced processing timelines, clear cost savings, or heightened accuracy).
• Proficiency with the Atlassian suite (Jira and Confluence).

Working Environment:

This is a remote position supporting Eastern Time business hours. Employees are expected to work 9:00 AM–5:00 PM ET unless otherwise directed by their manager. Occasional travel for training or project meetings may be required and is estimated at less than 5% annually.

Benefits:

eSimplicity offers a comprehensive benefits package, including medical, dental, and vision coverage, 401(k) retirement benefits, paid time off, paid holidays, life and disability insurance, and additional wellness and employee support programs. Eligibility may vary based on employment status and applicable plan terms.

Reasonable Accommodation:

eSimplicity is committed to providing reasonable accommodations to qualified individuals with disabilities during the application and hiring process. Applicants who need assistance or an accommodation should contact Human Resources.

Equal Employment Opportunity:

eSimplicity is an Equal Opportunity Employer, including disability and protected veteran status. All qualified applicants will receive consideration for employment without regard to race, color, religion, sex, sexual orientation, gender identity, national origin, age, protected veteran status, disability, or any other legally protected status