AI Solutions Architect

Job summary

Architect and deploy end-to-end GenAI and LLM-powered solutions from POC to production. Design RAG pipelines and agentic workflows while managing model evaluation, observability, and security.

Job details

Are you an AI Solutions Architect who has actually taken AI into production? Have you designed systems using LLMs, RAG, agents, vector search, and model orchestration beyond the POC stage? Do you want to help shape how a growing organization builds and scales production-grade AI? We’re working with a Toronto-based organization making a significant investment in AI and looking for someone who can bridge AI architecture, engineering, data, cloud, and the business. This is not simply a Software Engineer using AI tools to code. We’re looking for someone who has been responsible for architecting, integrating, deploying, and scaling AI systems in real production environments. What You’ll Do Architect end-to-end GenAI and LLM-powered solutions from POC through production. Design RAG pipelines, agentic workflows, model orchestration, and enterprise AI integrations. Build architectures across LLM APIs, embeddings, vector databases, data pipelines, APIs, and cloud infrastructure. Define approaches around model evaluation, observability, security, governance, and guardrails. Make architectural decisions around latency, scalability, reliability, cost, and model performance. Work across engineering, data, cloud, product, and business teams to turn AI use cases into production systems. You Are Experienced delivering LLM / GenAI systems into production, not just prototypes. Strong across RAG, embeddings, vector search, agents, prompt/model orchestration, and AI APIs. Comfortable with AWS/Azure/GCP, APIs, data architecture, distributed systems, and modern software architecture. Familiar with MLOps/LLMOps, evaluation frameworks, monitoring, AI security, and responsible AI practices. Able to translate complex business requirements into scalable AI architecture. Why This Role Real AI Engineering – production systems, not AI demos. Architecture Ownership – influence how AI is designed, integrated, governed, and scaled. Strong Compensation – up to $200K+ base. Toronto Hybrid – 2-3 days per week on-site.

What you’ll do

Architect and deploy end-to-end GenAI and LLM-powered solutions from POC to production. Design RAG pipelines and agentic workflows while managing model evaluation, observability, and security.

Requirements

Proven experience delivering production-grade LLM systems and expertise in vector databases and cloud infrastructure. Ability to translate complex business requirements into scalable AI architectures.

Listed skills

• Microsoft Azure · Preferred
• Amazon Web Services · Preferred
• Google Cloud · Preferred
• prompt engineering · Preferred

Other relevant skills

Identified from the job description. Confirm important requirements above.

• AI Architecture
• LLM
• RAG
• Vector Search
• Model Orchestration
• Agentic Workflows
• AWS
• Azure
• GCP
• MLOps
• LLMOps
• Data Architecture
• Distributed Systems
• AI Security
• Prompt Engineering
• Cloud Infrastructure

Job areas

• Technology
• Software
• Engineering
• Data & Analytics
• Science & Research