Senior AI/ML Engineer - RAG & LLM Systems (TS/SCI)

GRVTY; Town of Texas (WI); On-site; USD 175,000 - 225,000; Full time

Benefits offered by this job

Health plan

401k with company match

Paid time off

Parental leave

Training and development opportunities

Job summary

GRVTY is seeking a senior AI/ML engineer to own and advance Retrieval-Augmented Generation (RAG) workflows. You will implement RAG pipelines, integrate LLMs via APIs, and ensure robust REST interfaces for data retrieval and system integration. The role includes deploying self-hosted LLMs and conducting red-teaming of alignment challenges.

You will leverage Python and modern AI/ML libraries, engage in cutting-edge research, and collaborate with security-minded teams to meet mission requirements.

Qualifications

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

Responsibilities

• Implement and maintain RAG pipelines: document processing, embeddings, retrieval, prompts.
• Integrate LLMs into applications using available APIs/frameworks.
• Develop and maintain REST API interactions to support data retrieval and system integration.
• Deploy and maintain self-hosted LLMs.
• Conduct red-teaming of LLM alignment.

Skills

TS/SCI clearance

Polygraph clearance

Python

RAG/LLM AI

APIs & integration

Independent research

AI/ML frameworks

Education

Bachelor's degree

Master's degree

Doctorate

Tools

Docker

REST APIs

AWS/Cloud

Vector databases

Job description

GRVTY is seeking a senior AI/ML engineer to own and advance Retrieval-Augmented Generation (RAG) workflows. You will implement RAG pipelines, integrate LLMs via APIs, and ensure robust REST interfaces for data retrieval and system integration. The role includes deploying self-hosted LLMs and conducting red-teaming of alignment challenges.

You will leverage Python and modern AI/ML libraries, engage in cutting-edge research, and collaborate with security-minded teams to meet mission requirements.