GenAI Architect

This is a fully remote position, open to applicants in Canada.

📋 Description

• Oversee the complete architecture for LLM-driven assistants, agents, Custom GPTs, RAG solutions, and AI-enabled applications spanning experience, model, retrieval, orchestration, integration, security, cloud, deployment, and observability layers.

• Convert functional and non-functional use case requirements into detailed architecture documents, diagrams, integration patterns, data flows, security models, deployment designs, and implementation guidance.

• Choose suitable patterns, including prompt engineering, RAG, agentic orchestration, workflow automation, traditional software logic, or model customization—based on quality, risk, scalability, latency, cost, and supportability.

• Design solutions utilizing ChatGPT Enterprise, MCP-based applications, ChatGPT Skills, enterprise APIs, Databricks, vector search, governed data sources, and sanctioned AI platforms.

• Create agentic and event-driven solutions with OpenAI SDKs, LangChain / LangGraph, n8n, APIs, webhooks, and human-in-the-loop controls.

• Produce targeted proofs of concept and reference implementations to validate architectural decisions, mitigate delivery risks, and expedite engineering execution.

• Assist delivery teams in implementation while ensuring that delivered solutions align with approved architecture, security controls, engineering standards, and operational requirements.

• Perform solution and architecture reviews; identify technical risks, platform constraints, security gaps, data governance issues, and operational dependencies; and document decisions, assumptions, trade-offs, and recommendations.

• Create reusable reference architectures, solution patterns, technical standards, guardrails, and architecture decision records to facilitate enterprise GenAI adoption.

• Specify non-functional requirements addressing privacy, security, responsible AI, performance, scalability, observability, auditability, maintainability, and total cost of ownership.

• Establish safeguards against prompt injection, data leakage, unauthorized retrieval, insecure tool execution, excessive agency, secrets exposure, and inappropriate model outputs, ensuring proper human oversight for high-risk actions.

• Develop secure identity and access patterns utilizing OAuth, service identities, delegated authorization, role-based access control, secrets management, least privilege, and user-level auditability.

• Define evaluation, regression testing, red-teaming, tracing, monitoring, deployment, rollback, incident management, and operational readiness strategies for production GenAI systems.

• Assess emerging AI platforms and technologies while contributing to the GenAI capability roadmap by identifying platform deficiencies, reusable services, standard integrations, and strategic architectural enhancements.

• Collaborate with product owners, business leaders, engineering, data, platform, DevOps, cybersecurity, privacy, responsible AI, and enterprise architecture teams to transition solutions from concept to production.

• Lead architecture workshops and convey technical options, trade-offs, dependencies, risks, and recommendations to technical teams and senior stakeholders.

• Offer technical leadership across various GenAI initiatives, mentor engineers and solution designers, and support architecture consultations, design clinics, and technical office hours.

• Create concise architecture documents, technical specifications, implementation guidance, runbooks, and handover materials that promote long-term operational sustainability.

⛳️ Requirements

• Master’s degree with 6 or more years of relevant experience in Computer Science, Information Technology, Engineering, Data Science, or a related field; or Bachelor’s degree with 8 or more years of relevant experience in Computer Science, Information Technology, Engineering, Data Science, or a related field.

• A minimum of 6 years of progressive experience in software engineering, system design, cloud architecture, or solution architecture, including at least 2 years leading end-to-end technical design or serving as a lead engineer, technical architect, or solution architect.

• At least 2 years of hands-on experience architecting and delivering production GenAI applications, assistants, agents, Custom GPTs, or RAG solutions on ChatGPT Enterprise or similar enterprise AI platforms.

• Strong understanding of GenAI solution architecture, encompassing model selection, prompt and context design, RAG, embeddings, vector and hybrid retrieval, agent orchestration, tool integration, evaluation, guardrails, observability, and cost optimization.

• Proven experience defining comprehensive architectures across application, AI, data, integration, security, cloud, deployment, and operational layers.

• Demonstrated expertise in architecting secure, scalable, and production-ready solutions on AWS, employing managed AI services and cloud-native compute patterns such as AWS Lambda, Amazon ECS on AWS Fargate, and Amazon EC2, with strong knowledge of IAM, VPC networking, API Gateway, event-driven integration, observability, resiliency, and cost optimization.

• Experience designing secure enterprise integrations using REST APIs, event-driven patterns, OAuth, service identities, role-based access control, secrets management, and least-privilege access.

• Proficient in Python with experience developing prototypes, reference implementations, APIs, evaluation utilities, or integration components for GenAI solutions.

• Experience conducting architecture reviews, creating architecture artifacts, documenting decisions and trade-offs, defining non-functional requirements, and guiding engineering teams through implementation.

• Ability to articulate complex technical recommendations clearly to engineers, product owners, platform teams, business stakeholders, and senior leaders.

🏝️ Benefits

• Competitive and comprehensive Total Rewards Plans aligned with local industry standards.