LLM Architect – AWS Cloud, RAG Pipelines

Peraton; Reston (VA); On-site; USD 86,000 - 138,000; Full time

Benefits offered by this job

Remote-friendly?

Job summary

Peraton is seeking an LLM Specialist to drive design, development, and deployment of advanced language models within a cloud-based analytics environment. You will own finetuning, RAG pipelines, and domain adaptation while guiding scalable pipelines and governance.

The role requires hands-on Python development, experience with LangChain or LlamaIndex, and leadership across engineering, product, and data teams.

Qualifications

• Deep expertise in LLM architectures and generative AI techniques.

Responsibilities

• Design, develop, and operationalize advanced LLM capabilities in a cloud analytics ecosystem.
• Lead finetuning, RAG pipelines, and domain-specific model adaptation.
• Guide scalable LLM workflows and governance across deployments.
• Mentor team members and communicate complex AI concepts across audiences.

Skills

LLM architectures

Finetuning

LoRA/PEFT

RAG pipelines

Python

Cloud platforms (Azure/AWS/GCP)

MLOps/LLMOps

Technical leadership

Mentoring

Education

BS/BA

MS/MA

Tools

LangChain

LlamaIndex

Vector databases

Job description

Peraton is seeking an LLM Specialist to drive design, development, and deployment of advanced language models within a cloud-based analytics environment. You will own finetuning, RAG pipelines, and domain adaptation while guiding scalable pipelines and governance.

The role requires hands-on Python development, experience with LangChain or LlamaIndex, and leadership across engineering, product, and data teams.