About the Role

We are seeking an AI Engineer who is excited about the emergence of AI technologies and the potential and challenges that come with it. In this role you will implement agents who specialize in data extraction, enrichment, and integration to help us move traditional data processing into a dynamic and generalizable data pipeline that is driven by orchestration agents that are guided by data quality judge agents and governance agents that guide how agents behave in order to create more room for autonomous action while keeping data private, secure, and accurate.

Key Responsibilities

• Design, build, and deploy small-scale data extraction agents that leverage LLMs for structured information retrieval and summarization.

• Develop agentic strategies for joining structured and unscheduled data.

• Implement prompt-chaining and multi-agent orchestration frameworks to support adaptive, context-aware workflows.

• Develop and maintain “LLM-as-judge” evaluation loops for quality assurance, safety checks, and decision arbitration among autonomous agents.

• Contribute to the design of agent governance frameworks, including policy enforcement, alignment scoring, and auditing mechanisms.

• Collaborate with data engineers, ML researchers, and product teams to integrate agents into pipelines and user interactions.

• Monitor, evaluate, and iterate on model performance, latency, and reliability metrics in real-world use cases.

• Write clear, maintainable code and documentation for agent design and use.

• Stay current with advances in LLM architectures, tool-use capabilities, and AI governance trends.

Qualifications

We are a growth mindset driven company, if you don’t feel like you meet all these qualifications, but you are a fast learner or have other skills that relate to health, defence / emergecy management and AI, please do not disqualify yourself from applying for this role.

• Master Degree or Bachelor (with experience) in Computer Science or a related field

• 2–3 years of hands-on experience building or fine-tuning NLP/LLM systems or AI-driven automation workflows.

• Proficiency in Python and experience with frameworks like LangChain, LlamaIndex, or OpenAI SDKs.

• Familiarity with vector databases (e.g., Pinecone, Weaviate, FAISS) and retrieval-augmented generation (RAG) techniques.

• Understanding of LLM-as-judge methodologies (e.g., self-evaluation, pairwise scoring, and preference modeling).

• Experience with multi-agent systems, task routing, or agent governance design is strongly preferred.

• Strong analytical, communication, and documentation skills; comfortable translating research insights into practical engineering solutions.

Work Environment & Expectations

Based in Halifax, NS, with a hybrid work arrangement. Expected to be in the office in downtown Halifax at least two days per week to foster collaboration and team alignment.