AI Architect

Coforge; Canada; On-site; CAD 140,000 - 210,000; Full time

Job summary

Coforge Limited is seeking an experienced AI Architect to design an enterprise AI platform that enhances developer productivity, code quality, and engineering effectiveness. This hands-on role blends enterprise architecture with platform engineering to deliver secure, scalable AI capabilities across software workflows.

You will architect reusable platform services for governed LLM access, context engineering, RAG-driven retrieval, and observability, collaborating with security, cloud

Qualifications

• Proven experience in enterprise AI architecture, platform engineering, and production LLM integration.
• Hands-on experience with managed LLM services and enterprise AI governance patterns.
• Strong understanding of RAG, vector retrieval, context engineering, and AI workflow orchestration.
• Experience integrating enterprise platforms through APIs, webhooks, and modular abstraction layers.
• Strong knowledge of Azure cloud security, identity management, data protection, and observability.
• Experience with modern software engineering toolchains, CI/CD, source control, and application security practices.
• Ability to translate enterprise requirements into secure, scalable architectures and deliver pragmatic MVPs.
• Excellent communication and stakeholder management skills, with the ability to influence architecture decisions and mentor engineering teams.

Responsibilities

• Define the target-state AI architecture and implementation roadmap based on business value and risk.
• Design reusable platform capabilities for governed LLM access, context engineering, and enterprise knowledge retrieval.
• Integrate AI capabilities into developer workflows using GitHub Copilot, Azure DevOps, and related tools.
• Establish tool-agnostic integration patterns to support evolving engineering ecosystems.
• Define security controls, reference implementations, and operational runbooks for governance.
• Collaborate with Information Security, Cloud Engineering, Privacy, Risk, and AI governance stakeholders.

Skills

Enterprise AI architecture

AI platform engineering

LLM integration

Context engineering

RAG & vector retrieval

Observability

Azure cloud security

CI/CD

Stakeholder management

Tools

Azure DevOps

GitLab

GitHub

Jira

Confluence

REST APIs

Webhooks

CI/CD

Job description

We are looking for an experienced AI Architect to design and build an enterprise-grade, AI-enhanced software engineering platform that improves developer productivity, code quality, and engineering effectiveness.

This is a hands‑on architecture and platform engineering role focused on integrating enterprise AI capabilities into software development workflows. The ideal candidate combines strong enterprise architecture skills with practical experience building secure, scalable, governed AI platforms using managed LLM services.

• Enterprise AI Architecture & Platform Engineering – Designing and productionizing secure, reusable AI platforms using managed foundation‑model services.
• LLM Integration & Governance – Governed model access, AI gateways, model routing, authentication, usage controls, and cost monitoring.
• GitHub Copilot Enterprise – Enterprise adoption, model selection, licensing, usage governance, and developer workflow integration.
• Context Engineering – Prompt design, token management, structured outputs, tool calling, grounding, citations, and workflow orchestration.
• RAG & Vector Search – Retrieval‑augmented generation, embeddings, chunking, hybrid search, retrieval evaluation, Azure AI Search, and PostgreSQL with pgvector.
• Developer Toolchain Integration – Azure DevOps, GitLab, GitHub, Jira, Confluence, REST APIs, webhooks, CI/CD, and software development workflows.
• Cloud Security & AI Governance – Microsoft Entra ID, managed identities, Azure Key Vault, least‑privilege access, prompt‑injection defence, privacy, and auditability.
• Observability & Production Readiness – OpenTelemetry, Azure Application Insights, telemetry, performance monitoring, reliability, and cost optimization.
• Enterprise Knowledge Architecture – Knowledge modelling, metadata, taxonomies, provenance, and knowledge graphs where appropriate.
• Define the target‑state AI architecture, implementation roadmap, and prioritized MVPs based on business value, risk, and delivery effort.
• Design and implement reusable platform capabilities for governed LLM access, context engineering, enterprise knowledge retrieval, workflow orchestration, evaluation, and observability.
• Integrate AI capabilities into developer workflows, initially leveraging GitHub Copilot and Azure DevOps repositories, work items, pipelines, and service hooks.
• Design tool‑agnostic integration patterns to support evolving engineering ecosystems, including GitLab, Jira, and Confluence.
• Establish enterprise architecture standards, security controls, reference implementations, design documentation, and operational runbooks.
• Collaborate with Information Security, Cloud Engineering, Privacy, Risk, Architecture Review Board, and AI governance stakeholders.
• Partner with engineering teams through hands‑on implementation, technical guidance, design reviews, and knowledge transfer.
• Define evaluation and monitoring practices to measure AI quality, developer productivity, reliability, security, and cost effectiveness.

Required Experience

• Proven experience in enterprise AI architecture, AI platform engineering, and production LLM integration.
• Hands‑on experience with managed LLM services and enterprise AI governance patterns.
• Strong understanding of RAG, vector retrieval, context engineering, and AI workflow orchestration.
• Experience integrating enterprise platforms through APIs, webhooks, and modular abstraction layers.
• Strong knowledge of Azure cloud security, identity management, data protection, and observability.
• Experience with modern software engineering toolchains, CI/CD, source control, and application security practices.
• Ability to translate enterprise requirements into secure, scalable architectures and deliver pragmatic, production‑ready MVPs.
• Excellent communication and stakeholder management skills, with the ability to influence architecture decisions and mentor engineering teams.

What Makes This Role Unique?

This role offers the opportunity to shape an enterprise AI platform from architecture through implementation, enabling responsible AI adoption across software engineering teams.

The focus is on building practical AI capabilities, not training AI models - connecting approved LLMs, enterprise knowledge, and engineering tools through secure, reusable, and measurable platform services.