Overview
As a Senior Applied AI Engineer, you will play a pivotal role in developing and deploying agentic AI systems for high-stakes environments such as national security and critical infrastructure. Collaborating with a team of engineers, you will be responsible for creating reliable multi-agent systems that support confident decision-making under pressure. This position emphasizes strong engineering ownership and the delivery of dependable solutions from architecture through to production deployment.
Responsibilities
- Design and build multi-agent AI systems from the ground up.
- Write clean, tested, maintainable code and prioritize reliability and performance.
- Integrate large language and vision-language models into production pipelines.
- Deploy systems in cloud, on-premises, and offline environments, considering security constraints.
- Own the entire production pipeline from data ingestion to inference.
- Develop evaluation, observability, and guardrails for system performance.
- Set technical direction and documentation standards for subsequent engineering work.
Requirements
- Significant professional experience in software engineering (typically 6+ years), focusing on LLM-based or agentic systems.
- Strong fundamentals in software engineering with a track record of writing production-grade code.
- Commercial experience in building multi-agent AI systems end-to-end.
- Proficiency in Python and hands-on experience with LLM frameworks (LangGraph, LangChain, Haystack).
- Experience in designing and deploying AI/ML systems in real production scenarios.
- Familiarity with building search and retrieval systems over large multi-modal datasets (3TB+).
- Fluency in using Docker, Git, and cloud platforms (AWS preferred).
- Understanding of secure deployment patterns, including air-gapped and on-premises solutions.