Job Description
Gen AI Solution Architect
Location : Toronto – Hybrid (3–4 days WFO)
Role Overview
We are seeking an experienced Gen AI Solution Architect to design, build, and deploy reusable Generative AI modules across enterprise applications. The role combines technical leadership, product strategy, and adoption enablement , with a focus on LLM integration, RAG workflows, and scalable AI solutions.
The ideal candidate has deep experience in LLM / ML engineering , software architecture, API design, and enterprise platform development. This role will define product roadmaps, establish standards for Gen AI module reuse, and drive adoption across teams.
Key Responsibilities
Product Roadmap & Modular Design
Define the product vision and roadmap for reusable Gen AI modules (e.g., RAG, prompting frameworks, hybrid ML / LLM systems)
Architect parameterized, business-agnostic solutions that abstract complexity (pre-configured prompts, vector DB connectors, chunking logic)
Design APIs and microservices to expose modules as reusable components (e.g., text-to-SQL service, RAG-as-a-service)
Technical Leadership
Standardize patterns across use cases (prompt templates, chunking strategies, few-shot training pipelines)
Integrate LLM workflows (OpenAI, Claude, LLaMA 2) with traditional ML (clustering, classification) and enterprise systems
Optimize Gen AI component performance (cost, latency, accuracy) and ensure scalability (e.g., load balancing for vector DBs)
Adoption Enablement
Develop documentation, tutorials, and sandbox environments for testing modules
Train teams on best practices such as prompt engineering and security for LLM outputs
Metrics & Tracking
Track module reuse rate , contribution volume, and time-to-deploy for new use cases
Required Skills
Technical Expertise
Hands-on experience with LLM integration (OpenAI, Anthropic, LLaMA 2) and frameworks (LangChain, LlamaIndex)
Expertise in RAG workflows , document chunking (sentence transformers), vector DBs (Pinecone, FAISS), and hybrid search
Familiarity with text-to-SQL systems, few-shot / chain-of-thought prompting, and traditional ML (scikit-learn, PyTorch)
Software engineering proficiency in Python , API design (FastAPI, Flask), and cloud platforms (AWS Sagemaker, Azure AI)
Experience with CI / CD pipelines , containerization (Docker), and infrastructure-as-code (Terraform)
UI Integration Skills
Frontend integration using React or Streamlit for configuration UIs
Middleware integration with message queues and authentication systems (e.g., R2D2)
Product Strategy
Proven track record of building reusable ML / AI APIs or internal platforms
Ability to define product roadmaps and influence adoption across enterprise teams
Core Competencies
Generative AI / LLM architecture
RAG & hybrid ML workflows
API & microservices design
Enterprise AI platform strategy
Cloud-based AI solution deployment
Technical leadership & mentoring
Documentation & adoption enablement
Requirements
Experience (Years) : 4-6 Essential Skills :
Front End Developer Angular 13 • Toronto, ON, ca