Overview
The Senior Applied AI Engineer will be responsible for designing and building multi-agent AI systems that operate in critical environments. This role requires a high degree of technical ownership, where the engineer will create reliable AI solutions that inform consequential decisions for defense and national security applications. The position offers an opportunity to work in a hybrid model, collaborating with a fast-growing team focused on frontier AI technologies.
Responsibilities
- Design and build multi-agent AI systems from the ground up, utilizing frameworks like LangGraph or Haystack.
- Write clean, tested, and maintainable production-grade code while ensuring systems-level reliability.
- Integrate large language and vision-language models into effective reasoning, search, and task execution pipelines.
- Deploy AI systems in cloud, on-premises, and fully offline environments, addressing security and reliability constraints.
- Own the entire production pipeline from data ingestion to inference, ensuring accountability for system behavior.
- Establish evaluation and observability mechanisms to understand system performance and failure modes.
- Act as a technical authority for agentic AI, setting design patterns and direction for other engineers.
Requirements
- 6+ years of professional software engineering experience, preferably as a senior or lead engineer in LLM-based or agentic systems.
- Strong proficiency in Python with hands-on experience in building LLM frameworks such as LangGraph or Haystack.
- Experience in deploying AI/ML systems into real production environments beyond just demos or notebooks.
- Ability to manage large multi-modal datasets (3TB+) and ensure efficient indexing, embedding, and querying.
- Fluency with Docker, Git, and cloud platforms (AWS preferred); understanding of secure deployment patterns required.
- Strong documentation and knowledge transfer practices to ensure the sustainability of your deliverables.