AI/ML Security Integration Engineer

Bigbear.ai•Columbia, MD

2h•Onsite

About The Position

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.

Requirements

Bachelor's Degree with a Technical concentration with at least 10 years of professional experience
TS/SCI with an active Poly clearance
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

Nice To Haves

Experience deploying AI/ML models in classified or air-gapped environments
Knowledge of AI governance frameworks and ISO 42001 (AI management systems)
Familiarity with compliance automation use cases and security control frameworks
Experience with natural language processing (NLP) for technical documentation
Understanding of model evaluation metrics and AI accuracy assessment
Background in federal AI adoption requirements and responsible AI principles
Certifications: AWS Machine Learning Specialty, Azure AI Engineer, TensorFlow Developer
Experience with containerized AI deployments and MLOps practices

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