Overview
As a Senior Applied AI Engineer, you will play a pivotal role in developing agentic AI systems for critical environments where the stakes are high. Collaborating with a dynamic team, you will design and implement systems from the ground up, focusing on reliability and performance under real-world conditions. This position offers the unique opportunity to contribute to important decisions made across various sectors such as defence and national security, ensuring that the solutions you build earn the trust and confidence of stakeholders.
Responsibilities
- Build multi-agent AI systems from the ground up, using relevant frameworks and developing necessary infrastructure.
- Write clean, tested, and maintainable production-grade code, prioritizing reliability and performance.
- Integrate large language and vision-language models into decision and task execution pipelines.
- Deploy systems in complex environments including cloud and on-premises, addressing security and reliability challenges.
- Own the entire production pipeline from data ingestion to inference.
- Establish evaluation and observability protocols to assess system behavior and model performance.
- Act as a technical authority, setting standards and direction for the engineering team.
Requirements
- Minimum of 6 years of professional software engineering experience with a strong background in AI systems.
- Demonstrable experience building multi-agent or agentic AI systems in production environments.
- Proficiency in Python and experience with LLM frameworks such as LangGraph, LangChain, or Haystack.
- Familiarity with deploying AI/ML systems in real production settings, including secure environments.
- Experience working with large multi-modal datasets and associated data management techniques.
- Fluency with Docker, Git, and cloud platforms (preferably AWS).
- Understanding of secure deployment patterns like air-gapped and on-premises solutions.
- Track record of delivering dependable systems and effective documentation practices.