IntroductionBrunel is currently seeking a Agentic AI Engineer to support a government project on a remote (EST hours in Canada) Contract role. Role summaryWe are building AI-assisted automation for a large HR and payroll programme: agents and pipelines that turn business requirements and test-case workbooks into test cases, validated staging data and reviewer-ready evidence. We need a hands-on AI engineer to build, host and enhance these agents with us, take on delivery work using them, and bring new ideas on what AI can do next for HR and Pay.

The person writes production code, measures what it does, and ships. Extend our MCP (Model Context Protocol) server and APIs that agents call to read requirements, agreements, process maps, reference test cases and product documentation. Take agents from a local, single-user setup to a hosted service: containerized backend, identity and access control, audit logging, secrets management, deployment on Azure.

Build retrieval over HR and pay documents (collective agreements, process catalogues, test libraries): chunking, embeddings, hybrid search, re-ranking, with measured retrieval quality. Build labelled evaluation sets and regression tests for every AI feature; Connect outputs to Azure DevOps test management, and build Microsoft 365 agents (Copilot Studio, Agent Builder, Power Automate, Teams, SharePoint) for reviewer feedback and Q&A; inside the tenant. Run the pipelines on recent requirement workbooks, resolve what they flag, reconcile counts, and prepare outputs for review.

Propose and prototype new uses of AI across HR and pay testing: coverage analysis, scenario generation, defect triage,



process-to-requirement mapping. Python, 5+ years.

Production code on a shared codebase: typing, pytest, git branches and pull requests, code review. LLM application engineering, 12+ months shipped. Embeddings, vector stores, hybrid search, chunking strategy, and how to evaluate retrieval before building on it.

FastAPI or equivalent, Docker, REST, authentication and authorization, logging, deployment to Azure (App Service, Container Apps or AKS), CI/CD. Data handling. Messy multi-sheet Excel and CSV at scale with openpyxl or pandas; reconciliation that adds up; SQL.

AI-assisted development. Works fluently with AI coding assistants day to day and reviews their output critically. Clear written English; drafts precise questions when something is unclear.

Able to work with Government of Canada data: Microsoft 365 agent stack: Copilot Studio, Agent Builder, Power Automate, Power Platform, Azure AI Foundry, Semantic Kernel or Autogen. HCM or payroll platforms (Dayforce, Workday, SAP SuccessFactors, PeopleSoft) or public-sector HR and pay, including collective agreements and classification.

Document AI: PDF and image extraction, OCR, Visio or diagram parsing.

Security for AI systems: prompt injection defense, data boundaries, tenant DLP. French.

About

UsBrunel has a reputation for working with some of the best in the business. With 50 years of market experience in Renewable Energy, Automotive, Oil & Gas, Life Sciences, Mining and Infrastructure, we help you finish major projects safely, compliantly, on-time, within budget and at the highest quality, so you can keep growing – anywhere in the world. #

📌 Artificial Intelligence Engineer (Winnipeg)
🏢 Brunel
📍 Winnipeg