Principal AI Engineer

Job Description

Opentext - The Information Company OpenText is a global leader in information management, where innovation, creativity, and collaboration are the key components of our corporate culture. As a member of our team, you will have the opportunity to partner with the most highly regarded companies in the world, tackle complex issues, and contribute to projects that shape the future of digital transformation. AI-First. Future-Driven. Human-Centered. At OpenText, AI is at the heart of everything we do?powering innovation, transforming work, and empowering digital knowledge workers. We're hiring talent that AI can't replace to help us shape the future of information management. Join us. YOUR IMPACT We are seeking an accomplished Principal AI Engineer to lead the architecture, framework development, and production deployment of next-generation GenAI systems within enterprise-scale environments. This role demands deep expertise in LLM orchestration, multi-agent systems, and Retrieval-Augmented Generation (RAG) and Agentic workflows. You will architect reusable AI frameworks , define enterprise-grade standards , and guide engineering teams in delivering scalable, secure, and contextually intelligent AI solutions that power critical business functions globally. What The Role Offers Lead the next generation of enterprise AI engineering, defining frameworks used across global business domains. Collaborate with cross-functional teams pushing the frontier of Agentic AI, RAG, and MCP-based orchestration. Shape the strategic GenAI foundation for enterprise-scale applications. Be part of a world-class team committed to responsible, secure, and scalable AI innovation. AI Systems Architecture & Framework Development Architect and evolve enterprise AI frameworks enabling business teams to rapidly build domain-specific GenAI applications. Lead the design of multi-agent ecosystems leveraging protocols like A2A communication and MCP-based modular orchestration for scalable task decomposition and coordination. Define and implement production-grade AI infrastructure blueprints across cloud and hybrid environments for reliability, observability, and compliance. Build and optimize RAG pipelines integrating advanced context retrieval, adaptive prompting, and hybrid retrieval mechanisms. Engineering & Deployment Excellence Champion end-to-end AI system lifecycle, from experimentation to full-scale production, using robust LLMOps practices. Design and oversee containerized AI microservices using Docker, Kubernetes, and Helm optimized for cost, latency, and throughput. Drive CI/CD automation pipelines (GitLab, ArgoCD, Jenkins) with integrated testing, drift detection, and continuous model validation. Establish AI observability standards using OpenTelemetry, Prometheus, and Grafana for monitoring reliability and quality of agentic workflows. LLM Orchestration & GenAI Innovation Develop agentic frameworks (LangGraph, Crew AI, ADK) enabling reusable, configurable AI workflows across enterprise products. Lead initiatives around custom toolchains, knowledge-grounded inference, and LLM-powered business process automation. Guide experimentation with open-source and proprietary LLMs, including fine-tuning, PEFT/LoRA, and prompt optimization for specialized use cases. Implement semantic caching, dynamic memory, and reasoning-driven orchestration to improve responsiveness and reliability of GenAI systems. Strategic Leadership & Enablement Define AI architectural standards, reference implementations, and governance frameworks to ensure reusability and compliance. Mentor AI engineering teams to build scalable and interpretable GenAI systems aligned with business priorities. Collaborate with Product, Data, and Platform leaders to operationalize AI at scale across multiple business domains. Evaluate and integrate emerging technologies in multi-agent coordination, MCP, LLM distillation, and retrieval intelligence into enterprise frameworks. What You Need To Succeed Education: Bachelor?s or Master?s degree in Computer Science, Artificial Intelligence, Data Engineering, or related field Experience: 10?12 years of experience in AI/ML system engineering with a proven record of production-grade AI deployments at scale. Advanced hands-on experience with LangChain, LangGraph, CrewAI, or similar agentic/LLM frameworks. Expert-level understanding of RAG pipelines, LLM orchestration, and multi-agent architectures. Deep understanding of component abstraction, plugin design, and internal platform development. Proficiency in Python, FastAPI, and RESTful microservice design for AI systems. Deep hands-on expertise with vector databases (pgvector, Milvus, Weaviate, Pinecone) and semantic search systems. Proven track record with Docker, Kubernetes, Helm, and CI/CD automation (GitLab, ArgoCD, Jenkins). Extensive experience in AI observability, telemetry (OpenTelemetry), and model reliability engineering. Strong knowledge of data governance, privacy, and secure AI deployment within enterprise boundaries. Experience in Agent-to-Agent (A2A) architectures and MCP (Model Context Protocols) frameworks. Demonstrated ability to design AI platform SDKs/frameworks empowering non-technical users and developers. Hands-on experience in model optimization, inference acceleration, and LLM runtime tuning for cost and latency efficiency. Familiarity with AI cost management, tracing, and dynamic routing strategies in large deployments. Experience integrating LLMs with enterprise knowledge graphs, ERP, or ITSM systems for context-rich reasoning. Exposure to cloud-native AI platforms (AWS Sagemaker, Azure OpenAI, GCP Vertex AI). Practical experience with AI security, guardrails, red-teaming, and ethical AI principles. Strategic thinker with the ability to define and evangelize AI architecture vision across the enterprise. Exceptional communication skills to bridge technical and business teams. Proactive, results-oriented leader capable of driving innovation from concept to production. Passionate about agentic AI, retrieval intelligence, and self-optimizing AI systems that evolve with usage. OpenText's efforts to build an inclusive work environment go beyond simply complying with applicable laws. Our Employment Equity and Diversity Policy provides direction on maintaining a working environment that is inclusive of everyone, regardless of culture, national origin, race, color, gender, gender identification, sexual orientation, family status, age, veteran status, disability, religion, or other basis protected by applicable laws. If you need assistance and/or a reasonable accommodation due to a disability during the application or recruiting process, please contact us at [email protected]. Our proactive approach fosters collaboration, innovation, and personal growth, enriching OpenText's vibrant workplace.