Overview
As a Senior Applied AI Engineer, you will play a crucial role in developing and deploying advanced AI systems within mission-critical environments, particularly in defence and national security sectors. You will collaborate with a team of engineers to design and implement multi-agent AI systems with a strong focus on reliability and production readiness. This contract position allows for hybrid work, with a mix of remote and on-site responsibilities, primarily based in Oxford or London.
Responsibilities
- Design and build multi-agent AI systems from the ground up using suitable frameworks.
- Write clean, tested, maintainable code and prioritize reliability, latency, and failure behavior in system design.
- Integrate large language and vision-language models into reasoning, search, and task execution pipelines.
- Engineer systems for deployment in cloud, on-premises, and offline environments, addressing security and reliability constraints.
- Own the complete data pipeline from ingestion to inference, ensuring comprehensive technical oversight.
- Implement evaluation, observability, and guardrails for tracking system behavior and performance.
- Act as a technical authority, guiding other engineers and leaving behind maintainable documentation.
Requirements
- At least 6 years of professional software engineering experience, particularly in LLM-based or agentic systems.
- Strong foundation in software engineering, with a focus on producing clean, production-grade code.
- Experience building and owning multi-agent or agentic AI systems in live environments.
- Proficiency in Python and familiarity with LLM frameworks such as LangGraph, Haystack, or similar.
- Hands-on experience with the engineering surrounding models, including inference and data pipelines.
- Expertise in managing large multi-modal datasets (3TB+) for indexing and querying.
- Fluency with Docker, Git, and cloud platforms, preferably AWS.
- Understanding of secure deployment practices in regulated environments.