AI Agent Developer (Dynamics 365 / Dataverse)
- Toronto, ON
- Hybrid
- Posted Nov 18, 2026
- 1 position
$50–$58 / hour
Opens LinkedIn
- Employment type
- Contract
- Posting language
- English
- Office presence
- 3 days per week
Job summary
Design, build, integrate, test, and deploy reliable AI agents and multi-step workflows for business processes on Dynamics 365 and Dataverse, connecting them to APIs, enterprise data, and Azure services. Monitor and improve agents in production, implement safety and human-approval measures, review AI-generated code, and document solutions while collaborating with business and CRM stakeholders.
Job details
3 Days hybrid in Toronto, ON Experience 5+ years in software engineering, including hands-on work building AI agents or LLM-powered solutions Role Summary We are looking for an AI Agent Developer to design, build and run reliable AI agents that automate business processes on our Dynamics 365 and Dataverse platform. The person in this role will turn business requirements into agents that work dependably in production, connected to APIs, tools and enterprise data. Our team builds with AI-assisted engineering every day, using GitHub Copilot and the GitHub Copilot CLI. We value practical engineering and problem-solving over expertise in any single agent framework. The ideal candidate understands how agents behave, where they fail and how to make them dependable. Key Responsibilities Agent Design and Development Turn business requirements into clear, predictable and reliable agent behavior. Build AI agents and agentic workflows using GitHub Copilot (IDE, Chat and Agent mode) and the GitHub Copilot CLI. Design multi-step workflows, manage context and handle failures through retries, fallbacks and timeouts. Write and refine prompts, instructions and tool descriptions, with a clear understanding of LLM limitations. Integration with Tools and Data Connect agents to APIs, tools and data sources, including the Dataverse Web API, Dynamics 365, Power Automate and Azure services. Build retrieval (RAG) pipelines when agents need external knowledge. Testing, Quality and Safety Test, debug and evaluate agent behavior for accuracy, task completion and regressions. Add human approval steps for sensitive actions and protect agents against prompt injection. Review AI-generated code for correctness, security and performance before it is merged. Deployment and Operations Deploy agents through CI/CD pipelines (Azure DevOps or GitHub Actions) across Dev, Test and Prod. Monitor agents in production and improve them based on real usage, errors and feedback. Documentation and Collaboration Write clear design documents, runbooks and agent behavior specifications. Work with business stakeholders, product owners and CRM teams on requirements, UAT and rollout. Required Skills And Qualifications Area What We Look For LLM fundamentals Solid understanding of LLMs, prompting and their limitations AI-assisted development Hands-on, daily use of GitHub Copilot (IDE, Chat, Agent mode) and the GitHub Copilot CLI Tool and API integration Experience connecting agents to APIs, tools and data sources Workflow design Designing multi-step workflows, managing context and handling failures Testing and evaluation Strong problem-solving, testing, debugging and agent-evaluation skills Dynamics 365 / Dataverse Hands-on experience with Dynamics 365 CE / CRM, Dataverse and Power Platform Deployment Experience deploying, monitoring and improving applications Coding Good coding skills in Python, TypeScript or a similar language, enough to review, fix and improve AI-generated code Communication Clear documentation and collaboration skills
What you’ll do
Design, build, integrate, test, and deploy reliable AI agents and multi-step workflows for business processes on Dynamics 365 and Dataverse, connecting them to APIs, enterprise data, and Azure services. Monitor and improve agents in production, implement safety and human-approval measures, review AI-generated code, and document solutions while collaborating with business and CRM stakeholders.
Requirements
Requires 5+ years of software engineering experience, including hands-on development of AI agents or LLM-powered solutions, and practical daily use of GitHub Copilot and its CLI. Candidates should have experience with Dynamics 365 CE/CRM, Dataverse, and Power Platform, along with skills in API integration, workflow design, testing, deployment, monitoring, coding in Python or TypeScript, and clear communication.
Listed skills
- prompt engineering · Preferred
- Workflow Design · Preferred
- CI/CD · Preferred
- Python · Preferred
- TypeScript · Preferred
Other relevant skills
Identified from the job description. Confirm important requirements above.
- Large Language Models
- Prompt Engineering
- GitHub Copilot
- AI Agent Development
- Workflow Design
- API Integration
- Dynamics 365
- Dataverse
- Power Platform
- Retrieval-Augmented Generation
- Testing and Evaluation
- Prompt Injection Protection
- CI/CD
- Azure DevOps
- Python
- TypeScript
Job areas
- Technology
- Software
- Engineering
- Data & Analytics
More jobs from W3Global
ServiceNow Certified Technical Architect (CTA)
- On-site
- Posted Nov 18, 2026
Sr Mobility Developer
- On-site
- Calgary, AB
- Posted Nov 18, 2026
Senior Oracle Fusion Cash Management / Receivables Functional Consultant
- On-site
- Toronto, ON
- Posted Nov 18, 2026
Field Technician
- On-site
- Kitchener, ON
- Posted Nov 18, 2026
