Overview
The Senior Applied AI Engineer will be responsible for designing and building multi-agent AI systems that are crucial for decision-making in high-stakes environments such as defense and national security. Working in a hybrid capacity, the contractor will collaborate with a team of engineers to develop production-grade systems that meet rigorous reliability standards. This role emphasizes technical ownership and accountability for end-to-end system performance, requiring the engineer to engage deeply with both the architecture and deployment of AI systems.
Responsibilities
- Design and build multi-agent AI systems from the ground up using relevant frameworks.
- Write clean, tested, maintainable code while ensuring sound systems-level design decisions.
- Integrate large language and vision-language models into reasoning and task-execution pipelines.
- Deploy systems into cloud, on-premises, and offline environments, addressing associated security and reliability challenges.
- Own the entire production pipeline from data ingestion through to inference.
- Build evaluation and observability mechanisms to assess system behavior and performance.
- Provide technical leadership, establishing design patterns and maintaining documentation for future reference.
Requirements
- Significant professional software engineering experience (typically 6+ years), with a focus on LLM-based or agentic systems.
- Strong proficiency in Python and experience with frameworks like LangGraph, LangChain, or Haystack.
- Demonstrated experience in designing and deploying AI/ML systems into production environments.
- Expertise in handling large multi-modal datasets, including search and retrieval processes.
- Familiarity with Docker, Git, and cloud platforms, preferably AWS.
- Understanding of secure deployment patterns for AI systems.
- A builder's mindset with the ability to convey complex ideas to both technical and non-technical audiences.
- Strong documentation and knowledge transfer practices to ensure sustained project success.