AI Architect

BT-429 – AI Architect
Location: Tysons/McLean (fully on-site, no remote option)

• Design, architect, and prototype AI and Generative AI solutions that address complex mission and customer requirements.
• Develop AI architectures leveraging Large Language Models (LLMs), Generative AI, AI agents, and modern AI services.
• Develop solutions using Python for AI engineering, data processing, integrations, and prototyping.
• Apply prompt engineering techniques to optimize LLM performance and develop effective AI applications.
• Understand LLM context windows, tokenization, embeddings, and embedding models and how they impact AI application design.
• Design and implement AI agents, including agent orchestration, tool calling, and function calling.
• Configure, integrate, and interact with MCP (Model Context Protocol) servers to provide AI systems with access to external tools, services, and data.
• Design and integrate APIs supporting AI applications and interactions between services, models, and data sources.
• Incorporate OCR capabilities into AI architectures for extracting and processing information from documents and other unstructured data.
• Develop and leverage knowledge graphs, including an understanding of entities, relationships, and how they can support AI reasoning and information retrieval.
• Design architectures incorporating embedding models, vector databases, semantic search, and retrieval-based AI approaches.
• Design and integrate AI-powered chatbot and conversational interfaces.
• Develop mechanisms for source traceability, information verification, and reduction of AI hallucinations.
• Evaluate structured and unstructured data and determine the appropriate approach for preparing and making data available to AI systems.
• Design solutions that integrate ETL pipelines, batch processing, data lakes, and streaming data.
• Develop an understanding of data schemas and data models and how they support AI and data processing systems.
• Work with data ingestion and orchestration technologies such as Apache NiFi and Airflow.
• Design and deploy AI solutions using AWS cloud architecture, including services such as S3, EC2, IAM, VPC, Amazon Bedrock, and related AWS services.
• Evaluate existing data holdings, technical environments, and mission use cases to determine appropriate AI architecture and data strategies.
• Collaborate directly with high-level and senior customers to understand mission needs, communicate technical concepts, and recommend appropriate AI solutions.
• Lead technical discussions and communicate complex AI architecture concepts to both technical and non-technical stakeholders.
• Prototype and evaluate emerging AI technologies and determine their applicability to mission requirements.

• Strong Python
• Understanding of LLMs / GenAI architecture
• Understanding of OCR
• Understanding of Knowledge graphs and entities/relationships
• APIs
• Prompt Engineering
• Context Windows and Tokenization
• Embedding Models
• Agents and tool calling
• Setting up and hitting MCP Servers
• Function calling
• Good understanding of Cloud Architecture with AWS (S3, EC2, IAM, VPC, Bedrock, etc...)
• Understanding of ETL Pipeline and Batch Processing
  • Data Lakes
  • Streaming data
  • NiFi and Airflow
  • Understand data schemas / models
• Ability to work with high level/senior customers

• Experience developing or deploying GenAI agents in mission-driven environments.
• Experience with vector databases and semantic search.
• Experience with AI model optimization and evaluation.
• Experience designing cloud-native AI platforms and distributed systems.
• Experience implementing source traceability and verification mechanisms for AI-generated content.
• Experience with data cataloging, metadata management, and knowledge management.
• Experience with Java or other modern programming languages.
• AI, cloud, data science, or software engineering certifications.

• Bachelor's degree in Computer Science, Engineering, Data Science, Artificial Intelligence, or a related technical field.