Senior LLM Architect & RAG Lead

Peraton; Reston (VA); On-site; USD 104,000 - 166,000; Full time

Job summary

Peraton is seeking an LLM Specialist to drive the design, development, and deployment of advanced largelanguage model capabilities across a cloud analytics ecosystem. You will lead finetuning, RAG, and agentic frameworks, guiding prototype development and scalable pipelines with governance and security at the core.

You will mentor teams, evaluate new LLM tech, and shape best practices for safe, effective generative AI deployment across Azure/AWS/GCP environments.

Qualifications

• Eight-plus years experience with a BS/BA, six-plus years with MS/MA, or three-plus years with PhD.
• Deep expertise in transformer models and modern generative AI techniques.
• Proven ability to design end-to-end RAG pipelines with embedding workflows and vector DB integrations.

Responsibilities

• Drive design, development, and operationalization of advanced LLM capabilities.
• Lead governance, security, and performance across model implementations.
• Partner with engineering, product, and data teams to set best practices and drive safe deployment.

Skills

LLM architectures

Finetuning

RAG pipelines

LangChain

LlamaIndex

Python

Cloud platforms

MLOps/LLMOps

Technical leadership

Public Trust clearance

Education

BS/BA

MS/MA

PhD

Tools

LangChain

LlamaIndex

Azure

AWS

GCP

Job description

Peraton is seeking an LLM Specialist to drive the design, development, and deployment of advanced largelanguage model capabilities across a cloud analytics ecosystem. You will lead finetuning, RAG, and agentic frameworks, guiding prototype development and scalable pipelines with governance and security at the core.

You will mentor teams, evaluate new LLM tech, and shape best practices for safe, effective generative AI deployment across Azure/AWS/GCP environments.