AI Platform Engineer

As an AI Platform Engineer (LLM & MLOps) at GDIT, you will design, deploy, and operate secure, scalable AI inference and orchestration platforms that support USCENTCOM’s Data Analytical Environment (DAE) and AI environment. The focus is on platform reliability, workflow stability, and operationalizing commercial LLMs in on‑premises and hybrid environments.

• Design, deploy, and maintain GPU‑enabled Kubernetes environments for AI inference and orchestration.
• Operationalize commercial LLM inference services using frameworks such as Text Generation Inference, KServe, Fast Chat, Triton, or similar.
• Integrate vector databases and knowledge repositories to support Retrieval‑Augmented Generation (RAG) and graph‑augmented LLM workflows.
• Build and maintain secure REST APIs for AI job submission, inference requests, and workflow orchestration.
• Implement MLOps and platform lifecycle practices, including model versioning, containerization, CI/CD, and reproducibility.
• Enforce multi‑tenant isolation, RBAC, namespace quotas, and resource controls across teams.
• Implement monitoring, logging, and alerting for AI services, GPU utilization, and workflow health.
• Support secure deployment in air‑gapped, on‑prem, and hybrid environments, adhering to DoD security requirements.
• Collaborate with platform, automation, and data teams to align AI capabilities with mission workflows.
• Support prompt, rule, and heuristic‑based agents by ensuring reliable inference, retrieval, and context delivery.
• Maintain conversation‑aware context pipelines used for tagging and classification agents.

• Bachelor’s degree in Computer Science, Engineering, or a related technical field (or equivalent experience).
• Eight or more years of related experience.
• Strong experience with Kubernetes, containerization (Docker/Podman), and GPU scheduling.
• Hands‑on experience deploying LLM inference services (commercial or open‑source).
• Proficiency with Python and API development for platform services.
• Experience integrating vector databases such as FAISS, Milvus, Weaviate, or Open Search.
• Familiarity with MLOps tool chains (MLflow, CI/CD pipelines, artifact registries).
• Experience operating systems in secure DoD environments.
• Knowledge of monitoring/logging stacks (Prometheus, Grafana, ELK/Loki).
• DoD Directive 8140 compliance.

• Experience with Retrieval‑Augmented Generation or agent‑based AI architectures.
• Familiarity with Kubernetes‑native workflow engines such as Argo or Kubeflow.
• Exposure to cost tracking or usage metering for shared compute platforms.
• Understanding of DoD AI governance, ethical AI, and responsible deployment.

• Active Secret clearance required; TS/SCI preferred or eligible.
• U.S. citizenship required.

• Likely salary range: $127,500 – $172,500; final compensation based on experience, location, and contractual requirements.
• Comprehensive benefits package, including medical, dental, vision, 401(k) with company match, paid time off, and flexible work weeks.

• Weekly hours: 40.
• Travel: less than 10%.
• Telecommuting: onsite work required at Mac Dill AFB, Florida.

Equal Opportunity Employer / Individuals with Disabilities / Protected Veterans