LLM Systems Architect & Advisor: RAG, Governance, Cloud

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

Job summary

Peraton seeks an LLM Specialist to design, develop, and operationalize cutting-edge generative AI capabilities across a cloud-based analytics ecosystem. You will own architecture for finetuning, RAG, and domain-specific model adaptation, guiding high-impact prototypes and scalable pipelines.

You will partner with engineering, product, and data teams to drive governance, security, and performance, while advancing practical, safe deployment of AI.

Qualifications

• Deep expertise in LLM architectures and generative AI techniques.
• Experience leading finetuning, parameter-efficient training, and advanced prompt engineering.
• End-to-end RAG pipelines with embedding workflows, retrieval optimization, and vector DB integrations.
• Hands-on with LLM frameworks/orchestration tools like LangChain or LlamaIndex.
• Strong Python development and distributed/GPU training experience.
• Experience deploying AI/ML workflows on Azure AWS or GCP.
• Knowledge of MLOps/LLMOps including versioning, CI/CD, testing, monitoring, governance.
• Ability to mentor teams and explain AI concepts to non-technical audiences.
• Ability to obtain/maintain a Public Trust clearance.

Responsibilities

• Design, develop, and operationalize advanced LLM capabilities across a cloud analytics ecosystem.
• Lead architecture and strategy for finetuning, RAG, agentic frameworks, and domain-specific adaptation.
• Guide prototypes, evolve scalable LLM pipelines, ensure governance, security, and performance across models.

Skills

LLM architectures

Finetuning

RAG pipelines

LangChain/LlamaIndex

Python

Cloud platforms (Azure AWS GCP)

MLOps/LLMOps

Technical leadership

Public Trust clearance

Multiagent/agentic AI

RLHF style workflows

Retrieval techniques

Model optimization (quantization)

Databricks/Snowflake/Spark

Data modeling

Prototyping/POCs

Mixture-of-experts architectures

Education

BS/BA

MS/MA

PhD

Tools

LangChain

LlamaIndex

Job description

Peraton seeks an LLM Specialist to design, develop, and operationalize cutting-edge generative AI capabilities across a cloud-based analytics ecosystem. You will own architecture for finetuning, RAG, and domain-specific model adaptation, guiding high-impact prototypes and scalable pipelines.

You will partner with engineering, product, and data teams to drive governance, security, and performance, while advancing practical, safe deployment of AI.