Overview
As a Senior Applied AI Engineer, you will take a leading role in designing and building multi-agent AI systems for critical environments, where sound decisions are vital. You will be responsible for the end-to-end development of reliable AI solutions that integrate advanced models and frameworks, working closely with other engineers to set technical standards and ownership for the projects you lead. Your work will have a direct impact on national security and infrastructure, and you will be expected to deliver dependable systems under various operating conditions.
Responsibilities
- Design and build multi-agent AI systems from the ground up using relevant frameworks.
- Write clean, maintainable, and tested production-grade code, ensuring system reliability and performance.
- Integrate large language and vision-language models into reasoning and task-execution pipelines.
- Deploy systems in cloud, on-premises, and fully offline environments while addressing security constraints.
- Own the entire pipeline from data ingestion to inference, ensuring comprehensive system reliability.
- Build evaluation and observability tools that track system performance and reliability metrics.
- Act as a technical authority, guiding other engineers and documenting processes for future reference.
Requirements
- Minimum of 6 years of professional software engineering experience, particularly with LLM-based or agentic systems.
- Strong command of Python and experience with frameworks like LangGraph, LangChain, and Haystack.
- Proven experience in designing and deploying AI/ML systems in production environments.
- Ability to manage large multi-modal datasets (3TB+) and implement efficient retrieval and querying techniques.
- Familiarity with containerization using Docker and version control using Git.
- Understanding of deployment patterns for secure systems, including on-premises and air-gapped environments.
- Demonstrated ability to take technical ownership and deliver high-quality documentation and knowledge transfer.