ResponsibilitiesWe are seeking an Artificial Intelligence (AI) Solutions Architect as a senior technical authority on the CMS Fraud Prevention Services (FPS) team, owning the integration architecture that allows three external agentic AI vendors be onboarded into vendor-isolated enclaves inside the FPS ATO boundary. This role will develop AI solutions using Peraton tools to detect fraud, waste, and abuse.
Responsibilitie includes the following:
- Design the integration architecture for onboarding third-party agentic AI tools into vendor-isolated DISM enclaves inside the FPS ATO boundary.
- Author a common data package specification (schema, sampling strategy, PHI/PII handling, refresh cadence, packaging) that every evaluated vendor consumes.
- Define the per-vendor integration pattern for data access, identity federation, audit-log routing, and tenant isolation.
- Provide deep, hands-on LLM and agentic-AI expertise (RAG, fine-tuning, tool-use/MCP, multi-agent orchestration, LLMOps) to internal Peraton teams and CMS technical stakeholders.
- Ensure every architectural design embeds security, quality, PHI/PII, and governance controls appropriate to the FPS environment.
Qualifications
- Minimum of 8 years with BS/BA; Minimum of 6 years with MS/MA; Minimum of 3 years with PhD
- Deep hands-on expertise with LLM architectures and agentic AI systems: fine-tuning (LoRA/PEFT), RAG, prompt engineering, tool-use/MCP, multi-agent orchestration
- Ability to be highly independent and adaptive in a fast-changing environment.
- Has an AI first mentality and uses AI to accelerate productivity and software development.
- Demonstrated use of AI-driven coding and knowledge of best practices.
- Demonstrated experience designing integration architectures for third-party AI tools inside a customer's secure enclave (tenant isolation, identity federation, audit routing)
- Working experience with Snowflake and/or Databricks (Unity Catalog, MLflow, Delta Lake) plus strong SQL and Python.
- Experience deploying AI/ML workloads on AWS (VPC, IAM, KMS, S3, ECS/EKS, RDS, Bedrock or equivalent)
- Solid LLMOps/MLOps practice: versioning, evaluation harnesses, deployment automation, monitoring, governance.
- Familiarity with PHI/PII handling and access-controlled data storage.
- Strong written and verbal communication; able to present architectures to CMS technical and non-technical stakeholders.
- US citizenship; ability to obtain and maintain a Public Trust clearance.
Preferred Qualifications:
- Databricks E2 experience: Unity Catalog, Feature Store, MLflow registry, REST API integration.
- Experience with agentic frameworks such as Strands Agents, LangGraph, LlamaIndex, or CrewAI.
- Prior CMS or federal health environment experience (FPS, IDR, One PI).
- Knowledge of Medicare/Medicaid claims, NCD policy, and FWA/program-integrity use cases.
- Experience with Terraform/IaC, Argo CD, Helm for deploying platform components into AWS/EKS.
- Experience with vector databases, hybrid retrieval, graph retrieval, or long-context optimization.
- Confluence/JIRA in a SAFe Agile environment.
Target Salary Range$146,000 - $234,000. This represents the typical salary range for this position. Salary is determined by various factors, including but not limited to, the scope and responsibilities of the position, the individuals experience, education, knowledge, skills, and competencies, as well as geographic location and business and contract considerations. Depending on the position, employees may be eligible for overtime, shift differential, and a discretionary bonus in addition to base pay.
