AI/ML Security Integration Engineer

Job Description

Job Description

Overview

BigBear.ai is seeking an AI/ML Security Integration Engineer with an active TS/SCI clearance with a Poly, to configuring, fine-tuning, and maintaining an ATO Automation Platform’s Large Language Model (LLM) capabilities for secure operation within customer environments. This role ensures the AI components of the compliance automation platform function effectively while meeting stringent security requirements for federal deployments, including classified and air-gapped networks. This position will be based out of our Columbia, MD office but will support multiple customers in the Baltimore/Washington corridor and beyond.

Responsibilities

• Configure and optimize the ATO Automation Platform’s LLM backends (e.g. GPT-4, Claude Sonnet, Llama) based on customer security requirements and deployment constraints

• Implement and maintain the Retrieval-Augmented Generation (RAG) architecture that powers the ATO Automation Platform’s automated compliance documentation

• Develop and manage customer-specific knowledge bases incorporating organizational policies, security guides, and system documentation for AI processing

• Fine-tune LLM parameters and prompt engineering to ensure outputs match organization-specific documentation standards and terminology

• Implement secure data handling procedures for AI processing of potentially sensitive system configurations and security information

• Configure vector databases and enterprise search technologies that support the ATO Automation Platform’s compliance knowledge graph

• Monitor AI model performance and accuracy of generated compliance artifacts, implementing continuous improvement processes

• Deploy approved LLM models in restricted environments including air-gapped networks and classified systems

• Deploy and configure open-source Llama model in air-gapped DoD environment for processing IL5 system configurations

• Fine-tune Claude Sonnet prompts to generate control implementation descriptions matching agency-specific SSP format requirements

• Build custom RAG knowledge base incorporating customer’s 500+ security policies and standard operating procedures

• Implement data sanitization pipelines to redact classified markings before AI processing

• Optimize vector embedding strategies to improve the ATO Automation Platform’s accuracy in mapping code configurations to NIST 800-171 controls

Qualifications

• Bachelor's Degree with a Technical concentration with at least 10 years of professional experience
• TS/SCI with an active Poly clearance
• All applicants must currently reside in the United States
• Strong experience with Large Language Models and generative AI technologies (GPT-4, Claude, Llama)

• Proficiency in implementing Retrieval-Augmented Generation (RAG) architectures

• Experience with vector databases and semantic search technologies

• Programming proficiency in Python for AI/ML workflows and automation

• Understanding of prompt engineering and LLM fine-tuning techniques

• Knowledge of secure AI/ML deployment practices and data handling

• Experience with cloud-based AI services (AWS Bedrock, Azure OpenAI) and their government cloud implementations
• Understanding of cybersecurity principles and secure software development