Job Requirements
Chantilly, VA
Top Secret/SCI Polygraph not specified
Senior Level Career (10+ yrs experience)
$185,000 - $240,000
Job Description
Our client is a DoD-focused technology company building a classified, production-grade multi-agent AI coordination platform for U.S. Government environments at IL5 and IL6, including JWICS-connected deployments. This is a hands-on ownership role — not a DevOps-adjacent or configuration position — covering the platform from architecture through authorization.
Responsibilities will include, but are not limited to:
Own the full platform lifecycle — architecture, deployment pipelines, database and cache reliability, SLOs, and incident response — for a FastAPI/MCP server stack running on PostgreSQL (Aurora), Redis, and streamable HTTP/stdio transport layers
Architect and operate AWS GovCloud infrastructure at IL5/IL6, including C2S/SC2S connectivity, JWICS network patterns, cross-domain solution integration, and air-gapped deployment paths
Design and operate production LLM integrations (Claude, GPT, Gemini, or Bedrock-hosted models) including MCP server/client implementation, multi-agent orchestration, and LLMOps practices (versioning, evaluation, cost/latency instrumentation)
Build and maintain zero-downtime CI/CD pipelines with STIG-gated builds, SBOM generation, artifact signing, and automated security scanning
Implement and maintain FIPS 140-3 validated encryption, Zero Trust network architecture, and IAM/ABAC least-privilege designs for classified workloads
Drive FedRAMP High ATO activities including SSP authoring, control inheritance, continuous monitoring, and POA&M management
Minimum Qualifications:
Active TS/SCI clearance
7+ years of platform/infrastructure engineering with direct ownership of production systems
Proficiency in Python (FastAPI, asyncio, pydantic); Bash, Go, or Rust a plus
Expert-level PostgreSQL (schema design, RLS, replication, Aurora) and Redis (pub/sub, clustering)
Kubernetes and/or ECS Fargate experience
Terraform or AWS CDK with GitOps and policy-as-code workflows
Minimum 3 years hands-on AWS GovCloud experience, including at least 1 year in an IL5 or IL6 authorized environment
AWS Certified Solutions Architect – Professional AND AWS Certified Security – Specialty (both required)
Direct production experience integrating LLM APIs (Anthropic, OpenAI, Google, or Bedrock-hosted models)
MCP implementation experience — built or extended at least one MCP server or client in a production or research context
DoD 8570/8140 IAT Level II minimum (IAT Level III strongly preferred)
Applied experience with NIST 800-53, FIPS 140-3, and STIG hardening in production environments
FedRAMP High ATO process experience from the system owner or developer side
Preferred Qualifications:
CISSP, CCSP, Google Professional Cloud Security Engineer, or Microsoft SC-100
AWS Certified Machine Learning – Specialty or equivalent AI/ML certification
Experience with DoD software factory platforms (e.g., Platform One, Game Warden, or similar)
Active JWICS connectivity experience in a C2S/SC2S production environment
Air-gapped model hosting experience (vLLM, Ollama, or TGI)
SAFe or DoD Agile delivery experience on mission-critical programs
Familiarity with DARPA, CDAO, USSOCOM, MDA, or Space Force program structures
Physical Requirements:
This position requires the ability to remain in a stationary position for extended periods of time, operate standard office equipment such as a computer, keyboard, and telephone, and occasionally move about the work environment. Reasonable accommodations may be made to enable individuals with disabilities to perform the essential functions.
Responsibilities will include, but are not limited to:
Own the full platform lifecycle — architecture, deployment pipelines, database and cache reliability, SLOs, and incident response — for a FastAPI/MCP server stack running on PostgreSQL (Aurora), Redis, and streamable HTTP/stdio transport layers
Architect and operate AWS GovCloud infrastructure at IL5/IL6, including C2S/SC2S connectivity, JWICS network patterns, cross-domain solution integration, and air-gapped deployment paths
Design and operate production LLM integrations (Claude, GPT, Gemini, or Bedrock-hosted models) including MCP server/client implementation, multi-agent orchestration, and LLMOps practices (versioning, evaluation, cost/latency instrumentation)
Build and maintain zero-downtime CI/CD pipelines with STIG-gated builds, SBOM generation, artifact signing, and automated security scanning
Implement and maintain FIPS 140-3 validated encryption, Zero Trust network architecture, and IAM/ABAC least-privilege designs for classified workloads
Drive FedRAMP High ATO activities including SSP authoring, control inheritance, continuous monitoring, and POA&M management
Minimum Qualifications:
Active TS/SCI clearance
7+ years of platform/infrastructure engineering with direct ownership of production systems
Proficiency in Python (FastAPI, asyncio, pydantic); Bash, Go, or Rust a plus
Expert-level PostgreSQL (schema design, RLS, replication, Aurora) and Redis (pub/sub, clustering)
Kubernetes and/or ECS Fargate experience
Terraform or AWS CDK with GitOps and policy-as-code workflows
Minimum 3 years hands-on AWS GovCloud experience, including at least 1 year in an IL5 or IL6 authorized environment
AWS Certified Solutions Architect – Professional AND AWS Certified Security – Specialty (both required)
Direct production experience integrating LLM APIs (Anthropic, OpenAI, Google, or Bedrock-hosted models)
MCP implementation experience — built or extended at least one MCP server or client in a production or research context
DoD 8570/8140 IAT Level II minimum (IAT Level III strongly preferred)
Applied experience with NIST 800-53, FIPS 140-3, and STIG hardening in production environments
FedRAMP High ATO process experience from the system owner or developer side
Preferred Qualifications:
CISSP, CCSP, Google Professional Cloud Security Engineer, or Microsoft SC-100
AWS Certified Machine Learning – Specialty or equivalent AI/ML certification
Experience with DoD software factory platforms (e.g., Platform One, Game Warden, or similar)
Active JWICS connectivity experience in a C2S/SC2S production environment
Air-gapped model hosting experience (vLLM, Ollama, or TGI)
SAFe or DoD Agile delivery experience on mission-critical programs
Familiarity with DARPA, CDAO, USSOCOM, MDA, or Space Force program structures
Physical Requirements:
This position requires the ability to remain in a stationary position for extended periods of time, operate standard office equipment such as a computer, keyboard, and telephone, and occasionally move about the work environment. Reasonable accommodations may be made to enable individuals with disabilities to perform the essential functions.
group id: ClearanceJobsSC
