AI/ML Engineer - RAG, LLMs & API Integration

grvty; Sterling (VA); On-site; USD 175,000 - 225,000; Full time

Benefits offered by this job

Competitive benefits

Work-life balance

Paid time off

401k match

Training & development

Job summary

GRVTY is seeking a senior AI/ML engineer to own and evolve RAG pipelines, embed generation, and LLM integration in mission-focused applications at scale.

You will deploy self-hosted LLMs, design REST API interfaces, and perform red-teaming of alignment to ensure robust defenses, all while collaborating with teams across the organization.

Proven Python expertise and experience with AI/ML libraries, toolchains, and cloud/API integrations are essential for success.

Qualifications

• Active TS/SCI with ability to obtain a Polygraph Clearance.
• 8+ years of experience with a Bachelor's degree; or 7 years with a Masters; or 6 years with a Doctorate.
• Ability to conduct independent technical research and evaluate AI/ML approaches at PhD-level.
• Ability to rapidly learn and apply new AI/ML methodologies, tools, and frameworks.
• Experience developing AI/ML applications focused on Retrieval-Augmented Generation (RAG) or related workflows.
• Strong proficiency in Python and modern AI/ML libraries, frameworks, and API integrations.

Responsibilities

• Implement and maintain RAG pipelines, including document processing, embedding generation, retrieval configuration, and prompt assembly.
• Integrate LLMs into applications using available APIs and frameworks.
• Develop and maintain REST API interactions to support data retrieval and system integration.
• Deploy and maintain self-hosted LLMs.
• Red team LLM alignment efforts.

Skills

TS/SCI with Polygraph

Experience: 8+ years (Bachelor)

Experience: 7+ years (Master)

Experience: 6+ years (PhD)

AI/ML problem solving

Python proficiency

Education

Bachelor's degree + 8+ years

Master's degree + 7+ years

Doctorate + 6+ years

Tools

Docker

AWS

REST APIs

LLM APIS

Job description

GRVTY is seeking a senior AI/ML engineer to own and evolve RAG pipelines, embed generation, and LLM integration in mission-focused applications at scale.

You will deploy self-hosted LLMs, design REST API interfaces, and perform red-teaming of alignment to ensure robust defenses, all while collaborating with teams across the organization.

Proven Python expertise and experience with AI/ML libraries, toolchains, and cloud/API integrations are essential for success.