Position Overview

VStream Labs Inc. is seeking a hands-on AI Engineer – Agentic AI to design and deliver secure, production-ready AI applications, APIs, microservices, knowledge-graph capabilities, document-rendering workflows, and intelligent agentic systems. This remote contract requires strong software engineering, Azure integration, JVM and Python experience, AI evaluation, orchestration, governance, and production delivery.

Key Responsibilities

- Design, build, and deploy agentic AI solutions using LLMs, retrieval-augmented generation (RAG), memory, reasoning, prompt engineering, and human-in-the-loop patterns.
- Build backend services, REST APIs, and microservices using Node.js, Python, and JVM-based technologies.
- Develop and integrate knowledge graphs, entity and relationship models, graph-based retrieval, and GraphRAG capabilities.
- Build reliable document-generation and rendering pipelines, including HTML-to-PDF and comparable business-document transformations.
- Deploy and operate solutions using Azure App Service, Blob Storage, Key Vault, API Management, Entra ID, Azure OpenAI, and related cloud services.
- Implement OAuth 2.0 and OpenID Connect authentication and authorization.
- Integrate ServiceNow, Jira, Microsoft Graph, and other enterprise APIs.
- Evaluate AI systems using appropriate metrics and validation techniques; identify hallucinations, safety concerns, grounding issues, and model-performance risks.
- Implement workflow orchestration, observability, model monitoring, GitHub Actions, CI/CD, MLOps/LLMOps, and infrastructure as code.
- Apply secure engineering, responsible AI, governance, testing, and production-readiness practices.

What You Need to Have to Be Considered

- 8+ years of experience in AI/ML, Data Science, or Software Engineering.
- Strong understanding of machine-learning algorithms,



evaluation metrics, and model-validation techniques.
- Expertise in Agentic AI concepts, including LLMs, RAG, memory, reasoning, and prompt engineering.
- Hands-on experience building AI solutions using OpenAI, Azure OpenAI, Anthropic, Gemini, or similar platforms.
- Strong Python experience and practical experience with LangChain, LangGraph, Semantic Kernel, LlamaIndex, or comparable frameworks.
- Hands-on experience with the JVM ecosystem and integrating JVM-based applications or services.
- Solid Node.js development, REST API, and microservices experience.
- Experience with Azure App Service, Blob Storage, Key Vault, API Management, and Entra ID.
- Experience implementing knowledge graphs, graph data models, graph-based retrieval, or GraphRAG.
- Experience implementing production document-rendering solutions, including HTML-to-PDF or comparable document-generation pipelines.
- Proven experience evaluating AI systems, detecting hallucinations, and measuring model performance.
- Knowledge of scalable architecture, workflow orchestration, AI governance, and secure enterprise integration.
- Experience deploying production AI solutions using MLOps/LLMOps practices.
- Experience with GitHub Actions, CI/CD, and Git branching strategies.

These Will Help You Stand Out

- Experience with multi-agent systems and advanced orchestration frameworks.
- Cloud expertise in Azure, AWS, or Google Cloud.
- Knowledge of AI security, compliance, and responsible AI practices.
- Experience in regulated industries such as healthcare, insurance, or banking.
- Infrastructure-as-code experience.
- Relevant AI, ML, or cloud certifications.

Work Arrangement

- Contract
- Remote within Canada
- Compensation range: CAD $50–$55 per hour + HST
- Occasional collaboration during standard Canadian business hours may be required.

📌 Artificial Intelligence Engineer (Toronto)
🏢 VStream Labs
📍 Toronto