GenAI / Agentic Applications and DevSecOps Engineer Category: Architecture
Main location: Canada, Quebec, Montre9al
Position ID:J1026-1882
Employment Type: Full Time
Position Description: At CGI Montre9al, our Cloud and Artificial Intelligence practice is growing rapidly. We support large enterprises and organizations across industries and sectors in their digital transformation, cloud modernization, and generative AI initiatives. By joining our team, you will help design innovative, secure, and scalable solutions tailored to our clients' complex challenges.
Your future duties and responsibilities: Responsibilities
• Design, develop and deploy generative AI and agentic applications (assistants, RAG, multi-agent workflows and process automation) aligned with clients' business needs, in accordance with the standards and guardrails defined by the solution architect.
• Develop LLM-based applications and AI agents capable of using tools and APIs, including orchestration, memory, error recovery and human intervention.
• Build data pipelines for RAG: ingestion, chunking, embeddings, vector indexing, hybrid search and reranking.
• Implement and maintain CI/CD pipelines for AI applications, including automated testing, model evaluation, progressive deployment and rollback.
• Manage infrastructure as code and container platforms (Docker, Kubernetes) in cloud environments.
• Integrate automated security controls into delivery pipelines (SAST, SCA, secrets detection, container and IaC scanning, SBOM), in collaboration with application security teams.
• Implement AI-specific protections: input and output filtering, prompt-injection protection, agent permission management and personal information protection.
• Build evaluation datasets and automated response-quality tests, and instrument applications for observability (traces, latency, token consumption and costs).
• Operate AI solutions in production: monitoring, incident management, cost control and continuous improvement.
• Document solutions, share reusable patterns with internal teams and stay current with developments in generative AI, agent frameworks and DevSecOps tools.
Required qualifications to be successful in this role: Required qualifications
• At least 5 years of experience in software development or DevOps engineering, including at least 2 years focused on generative AI or LLM-based solutions.
• Excellent command of Python and at least one other language (TypeScript, Java, C# or Go).
• Hands-on experience with managed LLM services (Azure OpenAI, AWS Bedrock, Google Vertex AI) and models (GPT, Claude, Llama, Mistral).
• Strong knowledge of agent and orchestration frameworks (LangChain / LangGraph, Semantic Kernel, LlamaIndex), RAG architectures, vector databases, tool calling and agent protocols such as MCP.
• Proficiency with DevSecOps practices and tools: Git, CI/CD (GitHub Actions, GitLab CI, Azure DevOps), Docker, Kubernetes and Terraform.
• Experience with at least one major cloud platform (Azure, AWS or GCP).
• Knowledge of secure development practices, application security tools (SAST, SCA, secrets detection) and AI-specific security risks (OWASP Top 10 for LLM applications).
• Ability to explain the capabilities and limitations of AI to non-technical stakeholders.
• Bilingual in French and English.
Assets
• Cloud, AI or security certification (e.g., Azure AI Engineer Associate, AWS Certified Machine Learning Engineer, Certified Kubernetes Administrator, Certified DevSecOps Professional).
• Experience with LLM evaluation and observability tools (Langfuse, LangSmith, OpenTelemetry).
• Daily use of AI coding agents and AI-assisted development tools.
• Experience delivering solutions in regulated environments (public sector, financial services, healthcare).
• Knowledge of AI-related standards and regulatory frameworks (Que9bec Law 25, EU AI Act, NIST AI RMF, etc.).
Use of the term 'engineering' in this job posting refers to the technical sense related to Information Technology (IT) and does not imply that the individual practices engineering or possesses the requisite license as prescribed by the applicable provincial or territorial engineering regulator. We are seeking individuals with expertise in IT engineering-related functions, but licensure from an engineering regulator is not a prerequisite for this position. Engineering is a regulated profession in Canada which is restricted in terms of use of titles and designation.
Skills: - Azure
- DevOps
- Docker
- Java
- Kubernetes
- Python
- Typescript
