Specialist, AI Solutions

Samuel, Son & Co.•Oakville, ON

2d•CA$90,080 - CA$123,860

About The Position

This role focuses on designing and developing production-grade AI solutions, particularly leveraging Large Language Models (LLMs), Context Engineering, Retrieval-Augmented Generation (RAG), and classical machine-learning techniques. The Specialist will define standards for Agent design and orchestration, develop reusable patterns for prompts and context, and integrate AI capabilities into enterprise applications. A significant part of the role involves working with Microsoft Azure AI services, including Azure AI Foundry, Azure App Services, and various AI services like Vision, Speech, and Language. The position also requires data engineering skills using Microsoft Fabric for data ingestion, transformation, and curation, as well as preparing data for RAG and embeddings. Core development responsibilities include building UI components, implementing observability, and establishing MLOps/DevOps pipelines. Collaboration with various stakeholders is essential.

Requirements

Hands-on with Large Language Models, prompt and context engineering, RAG, feature engineering, ML model development, and AI-assisted coding tools (GitHub Copilot, Cursor, Claude Code).
Azure infrastructure and cloud-based AI service deployment, plus working knowledge of Azure Container Apps, App Services, and Azure DevOps pipelines.
Fabric Pipelines, Delta Tables, and Fabric Notebooks (PySpark); Lakehouse and Data Warehouse patterns; event-driven (RTI) architecture.
Building data ingestion pipelines, data curation with SQL and Python, and data cleansing/deduplication; Fabric Notebook.
Python for AI/ML and automation; TypeScript, React/Next.js, Node.js for full-stack and dashboards; PySpark for distributed processing.
REST and GraphQL API development with OpenAPI/Swagger specifications.
Power BI report design, DAX, semantic models, and Fabric DirectLake integration; conceptual, logical, and physical data modeling.
Advanced Git source control and branching strategies; CI/CD, containerization, and infrastructure-as-code practices.
Application Insights, telemetry, custom metrics, distributed tracing, alerting, and Azure observability platforms.
Bachelor’s degree in Computer Science, Information Systems, Engineering, or equivalent professional experience.
3+ years of hands-on experience building production software, with at least 2 years focused on AI solutions and cloud-native data solutions.

Nice To Haves

Relevant Microsoft certifications preferred: Azure AI Engineer Associate (AI-102), Azure Data Engineer Associate (DP-203), and Fabric Analytics Engineer Associate (DP-600).

Responsibilities

Design and build production-grade AI solutions leveraging Large Language Models (LLMs), Context Engineering, Retrieval-Augmented Generation (RAG), and classical machine-learning techniques.
Define Agent design development standards and orchestration Design Patterns.
Develop reusable prompt, context, and feature engineering patterns to improve model accuracy, grounding, and performance.
Integrate AI capabilities into enterprise applications using REST and GraphQL APIs, OpenAPI/Swagger specifications, and Azure-native services.
Use AI-assisted development tools (GitHub Copilot, Cursor, Claude Code) to accelerate delivery while maintaining code quality and review standards.
Design & Build AI Solutions: Develop and deploy AI applications on Microsoft Copilot, Azure AI Foundry, Azure App Services.
API & Service Integration: Connect Azure AI services (Vision, Speech, Language, Document Intelligence) to existing applications using REST APIs and Python/C# SDKs.
RAG & Knowledge Mining: Build Retrieval-Augmented Generation (RAG) pipelines with Azure AI Search to ground AI responses in enterprise data.
Responsible AI Guardrails: Apply content safety, prompt shields, and PII filters via Azure AI Content Safety to ensure compliant AI deployments.
Build and maintain data ingestion, transformation, and curation pipelines using Microsoft Fabric Pipelines, Fabric Notebooks (PySpark), and Delta Tables.
Utilize Lakehouse and Data Warehouse patterns following the standards prepared by Data Engineering teams.
Prepare the Context of AI Agents through the use of data preparation and data pipeline orchestration.
Prepare high-quality data for RAG, embeddings, and vector search through profiling, cleansing, validation, and deduplication.
Building interactive UI components in React/Next.js/JavaScript for AI applications and dashboards – utilizing AI coding assistance.
Application Insights, telemetry, alerting, and performance monitoring.
MLOps & DevOps: Build CI/CD pipelines in GitHub Actions or Azure DevOps to register, test, and deploy models.
Collaborative communication with engineering, analytics, architecture, and business stakeholders.