Senior LLM / RAG Engineer

Peraton • Reston, VA

2d

About The Position

We are looking for a Senior‑Level Engineer to lead the development and sustainment of Retrieval‑Augmented Generation (RAG) AI prototypes for a national‑security mission. You will work directly with customer stakeholders to expand an existing prototype and deliver new LLM‑powered capabilities that help analysts understand and act on large volumes of proprietary data. In this role, you will combine data engineering, model serving, GPU‑based inference, and rapid application development to deliver high‑impact AI tools in a secure environment.

Requirements

• Bachelor’s degree in an area relevant to the position with 12+ years of applicable experience OR a Master’s degree in an area relevant to the position with 10 years of applicable experience; an additional 4 years of applicable experience maybe considered in lieu of a degree.
• Active TS/SCI or SCI eligibility and active polygraph or ability to obtain a polygraph
• Strong hands‑on experience with AWS services (EC2, S3, IAM, container services)
• Expertise with Python and Linux in operational environments
• Ability to design, deploy, and manage Docker‑based workloads
• Experience with GPU inference, model serving, and LLM fundamentals
• Experience working with structured, semi‑structured, and unstructured data
• Familiarity with CI/CD basics (Git, Jenkins, etc.)

Nice To Haves

• Streamlit or similar tools for rapid UI development
• Experience with vector stores (Milvus or comparable)
• Familiarity with embedding generation and RAG pipeline tooling
• Experience with sglang, Ray Serve, LlamaIndex, Hugging Face, or similar frameworks
• AWS certifications
• Knowledge of prompt engineering and evaluation best practices

Responsibilities

• Maintain and extend current RAG prototypes to integrate new datasets and features
• Build and optimize data ingest pipelines using Python and AWS services
• Develop LLM/embedding pipelines and operate GPU inference workloads
• Deploy and manage containerized services in Kubernetes‑like or Docker‑based environments
• Implement vector search solutions using modern vector databases
• Develop mission‑focused UIs using Streamlit or similar tools for rapid prototyping
• Use tools such as sglang, Ray Serve, and LlamaIndex to operationalize LLM capabilities
• Collaborate closely with analysts and mission leaders to understand use cases and rapidly iterate on prototypes
• Ensure solutions follow customer security, compliance, and operational guidelines
• Write technical documentation for deployments, APIs, and system behaviors

Benefits

• Heavily subsidized employee benefits coverage for you and your dependents
• 25 days of PTO accrued annually up to a generous PTO cap
• Eligible to participate in an attractive bonus plan

What This Job Offers

• Job Type: Full-time
• Career Level: Senior