Job Title: AI Solutions Architect
12-month contract | Hybrid in the Greater Vancouver Metropolitan Area | Must hold a valid Canadian Work Visa
Our client, a leading provincial organization dedicated to workplace health, safety, and injury prevention, is seeking an experienced Senior AI Solutions Architect for a 12-month hybrid contract in the Greater Vancouver area.
The Senior AI Solutions Architect will provide architectural leadership and technical direction for a portfolio of AI-native application development and modernization initiatives. This is a senior, architecture-focused role that requires strong hands-on engineering capabilities, combining enterprise solution architecture with the practical design, development, and deployment of production-grade AI-powered applications on Microsoft Azure.
Working closely with a cross-functional AI software development team, the successful candidate will own the end-to-end solution architecture, from requirements gathering and technical design through implementation, testing, and production deployment. A key focus will be establishing and operationalizing an AI-Native Software Development Lifecycle (SDLC) that leverages AI-assisted development tools, agentic workflows, automation, and modern engineering practices to accelerate delivery while maintaining quality, security, and governance standards.
The role will involve designing and implementing solutions using Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), agentic AI frameworks, multi-agent orchestration, and Azure AI services. The Architect will also establish reusable engineering standards, reference architectures, development playbooks, and quality assurance frameworks to support broader adoption across the organization.
The ideal candidate brings extensive experience in enterprise solution architecture and software engineering, with recent hands-on experience delivering AI-powered applications into production. This position requires someone who can operate as a principal architectural authority while remaining technically proficient at the code level, providing mentorship and guidance to senior developers and engineering teams.
Responsibilities:
- Own the end-to-end solution architecture for AI-native applications and enterprise application modernization initiatives, defining logical components, interfaces, integration patterns, and foundational model selection
- Establish and operationalize an AI-Native Software Development Lifecycle (SDLC) covering requirements intake, solution design, development, testing, deployment, and production support
- Develop reusable technical playbooks, Architecture Definition Documents (ADDs), Architecture Decision Records (ADRs), reference architectures, engineering standards, and operational runbooks
- Translate business objectives and requirements into scalable, secure, and maintainable technical solutions
- Validate architectural decisions through hands-on prototyping, proof-of-concept development, and reference implementations
- Design and build reference applications using C#, ASP.NET, .NET 10, Python, and Microsoft Azure, incorporating appropriate monitoring, logging, and observability capabilities
- Architect and implement Retrieval-Augmented Generation (RAG) pipelines, including embeddings, retrieval strategies, re-ranking, and vector storage solutions
- Evaluate and implement vector databases and search technologies such as Azure AI Search, Azure Cosmos DB, pgvector, and Qdrant
- Design reusable agentic AI and multi-agent orchestration patterns using frameworks such as Semantic Kernel, AutoGen, CrewAI, LangGraph, LangChain, and LlamaIndex
- Integrate LLMs and AI capabilities into enterprise applications using Azure OpenAI, OpenAI APIs, and open-source models
- Define prompt engineering strategies, prompt versioning, memory management, task chaining, and evaluation approaches using tools such as PromptFlow or Prompty
- Select, configure, and operationalize AI-assisted software development tools, including GitHub Copilot, Cursor, agentic development tools, and AI-enabled code review workflows
- Establish standardized development workflows incorporating AI-assisted coding, automated testing, code review, and developer productivity improvements
- Define and implement CI/CD pipelines, deployment processes, automated quality gates, release controls, and rollback procedures for AI-native applications
- Ensure AI-assisted development activities comply with established enterprise change management, security, testing, and production readiness requirements
- Integrate static code analysis, dependency scanning, secret detection, code quality checks, and review controls for AI-generated code
- Design and implement AI evaluation and quality assurance frameworks, including LLM evaluations, automated regression testing, red-teaming, safety testing, and quality gates
- Establish comprehensive AI observability and tracing capabilities using technologies such as Azure Monitor, Application Insights, Dynatrace, LangSmith, MLflow Tracing, and OpenTelemetry
- Ensure solutions comply with privacy, security, data residency, regulatory, and responsible AI requirements, collaborating with security teams on AI-specific threat modeling
- Evaluate the effectiveness of AI-native development practices against traditional delivery approaches, measuring development velocity, defect density, automation coverage, and delivery costs
- Prepare and present pilot outcomes, measurable benefits, technical risks, and recommendations for scaling AI-native development practices
- Deliver a reusable AI-Native SDLC adoption framework, including technical playbooks, reference architectures, toolchain configurations, governance checkpoints, security controls, and deployment checklists
- Provide technical leadership, architecture guidance, code reviews, and mentorship to senior developers and engineers, promoting consistent engineering standards and best practices
Qualifications:
- Undergraduate degree in Computer Science or a related STEM discipline; an equivalent combination of education and experience may be considered
- 12+ years of progressive experience in software development, solution architecture, or systems architecture, including recent hands-on delivery involving LLMs and AI integration
- Demonstrated experience designing and delivering AI-powered applications, including LLM-based solutions, RAG pipelines, and agentic systems, from prototype through stable production deployment
- Extensive experience defining enterprise solution architectures, engineering standards, Architecture Definition Documents, technical playbooks, and reference architectures
- Strong hands-on software development experience with Python and C#/.NET Core, including object-oriented design and modern software engineering practices
- Experience with ASP.NET and .NET 8/10 for cloud-native applications and APIs is preferred
- Practical experience with agentic AI orchestration frameworks, such as Semantic Kernel, LangGraph, AutoGen, or CrewAI
- Experience with AI/ML development frameworks and tools, including OpenAI SDKs, LangChain, and Hugging Face
- Strong understanding of RAG and GraphRAG architectures, embeddings, vector search, and vector databases, including technologies such as Azure AI Search, Cosmos DB, pgvector, or Qdrant
- Experience developing and executing AI evaluations, LLM regression tests, automated quality gates, and AI-driven testing frameworks
- Expert knowledge of designing and implementing cloud-native solutions on Microsoft Azure, including microservices, containers, CI/CD pipelines, and MLOps practices
- Strong experience with Azure OpenAI Service, including enterprise integration patterns, security considerations, and production deployment
- Experience with Azure services such as Azure App Service, Azure Functions, Azure Container Apps, Azure SQL, Azure Key Vault, Azure DevOps, and Azure Monitor
- Strong understanding of APIs, Git, Agile software development methodologies, and enterprise application integration
- Hands-on experience using AI coding assistants and agentic development tools, such as GitHub Copilot, Cursor, or comparable technologies, is preferred
- Experience with AI evaluation and benchmarking platforms, such as Azure AI Evaluation SDK or DeepEval, is considered an asset
- Familiarity with AI observability and tracing tools, including Dynatrace, LangSmith, MLflow Tracing, Weights & Biases, or PromptFlow, is an asset
- Experience with Infrastructure as Code (IaC) tools such as Terraform or Bicep is preferred
- Understanding of AI security, privacy, responsible AI, data governance, and regulatory compliance within enterprise environments
- Experience working within regulated industries, such as insurance, healthcare, government, or financial services, is considered an asset
- Microsoft Certified: Azure Solutions Architect Expert or AWS Certified Solutions Architect certification is preferred
- Demonstrated ability to provide technical leadership, architectural direction, mentorship, and code review to senior developers and engineering teams
- Strong analytical and problem-solving skills, with the ability to evaluate complex architectural trade-offs and recommend practical solutions
- Excellent written and verbal communication skills, including the ability to explain complex AI concepts, technical decisions, and architectural recommendations to both technical and non-technical stakeholders
- Strong collaboration and stakeholder management skills, with experience working across cross-functional engineering, architecture, security, operations, and business teams
NOTE: Interested candidates who meet the above qualifications are encouraged to apply directly. Due to the volume of applications, only those shortlisted will be contacted.
