Principal SI Platform Engineer
Core
Design, develop, deploy, and support Retrieval-Augmented Generation (RAG) solutions and Large Language Model (LLM) orchestration in high-performance computing Linux environments for mission-critical U.S. Government applications.
Role type
Principal Staff Platform Engineer (Generative AI/SI)
Builds
Scalable, production-ready RAG architectures, LLM inference pipelines, and containerized AI systems.
Domain
U.S. Government Intelligence / Generative AI / High-Performance Computing
Deliverable
production ML models
Required skills
Linux system administration, Python software development, Kubernetes, Docker/Podman, CI/CD pipelines, RAG architectures, LLM orchestration, vector databases, embedding models, DevSecOps, Git workflows
Preferred skills
AWS Cloud, GPU-enabled applications, PyTorch/TensorFlow, KubeFlow, SQL, Elasticsearch, vLLM/Nvidia NIM/Triton, Atlassian tools
Technologies
AWS, Kubernetes, Docker, Podman, GitLab CI/CD, Prometheus, Grafana, PyTorch, TensorFlow, vLLM, Triton, Elasticsearch, SQL, Helm, Confluence
Responsibilities
Design and develop RAG solutions using LLMs and knowledge retrieval systems; Deploy and manage containerized AI applications; Maintain CI/CD pipelines and monitoring platforms; Support mission-critical SI system development in HPC environments.
Seniority
Principal, hands-on IC with strategic oversight
