Overview
The Senior Applied AI Engineer will design and build production-grade agentic AI systems for defense and national security applications, ensuring high reliability and trustworthiness in mission-critical environments. This role involves collaborating with cross-functional teams to develop innovative solutions that meet stringent performance and security standards, while also focusing on end-to-end ownership of systems that have real-world implications.
Responsibilities
- Design and build multi-agent AI systems from the ground up, applying relevant frameworks as necessary. Write clean, tested, maintainable production-grade code, prioritizing reliability and performance. Integrate large language and vision-language models into reasoning and task execution pipelines. Deploy systems into challenging environments, ensuring security and reliability. Own the production pipelines from data ingestion to inference, ensuring comprehensive oversight. Develop evaluative and observability tools to monitor system performance and behavior. Provide technical authority for agentic AI, setting design patterns and guiding engineering practices.
Requirements
- Minimum 6 years of professional software engineering experience, including experience with LLM-based systems. Proven track record in building multi-agent or agentic AI systems in production. Strong programming skills in Python, including hands-on experience with frameworks such as LangGraph, LangChain, or Haystack. Solid understanding of model engineering, performance, and data pipelines. Experience managing large multi-modal datasets and implementing search and retrieval systems. Proficiency in Docker, Git, and cloud platforms, preferably AWS. Familiarity with secure deployment patterns and principles of secure-by-design development. Active SC clearance is a significant advantage.