AI Engineer

Overview: Guidepoint seeks an experienced AI Engineer as an integral member of the Toronto-based AI team. The Toronto Technology Hub serves as the base of our Data/AI/ML team, dedicated to building a modern data infrastructure for advanced analytics and the development of responsible AI. This strategic investment is integral to Guidepoint’s vision for the future, aiming to develop cutting-edge Generative AI and analytical capabilities that will underpin Guidepoint’s Next-Gen research enablement platform and data products. This role demands exceptional leadership and technical prowess to drive the development of next-generation research enablement platforms and AI-driven data products. You will develop and scale Generative AI-powered systems, including large language model (LLM) applications and research agents, while ensuring the integration of responsible AI and best-in-class MLOps. The AI/ML Engineer will be a primary contributor to building scalable AI/ML capabilities using Databricks and other state-of-the-art tools across all of Guidepoint’s products. Guidepoint’s Technology team thrives on problem-solving and creating happier users. As Guidepoint works to achieve its mission of making individuals, businesses, and the world smarter through personalized knowledge-sharing solutions, the engineering team is taking on challenges to improve our internal application architecture and create new AI-enabled products to optimize the seamless delivery of our services. This is a hybrid position based in Toronto. What You'll Do: Architect and Build Production Systems: Design, build, and operate scalable, low-latency backend services and APIs that serve Generative AI features, from retrieval-augmented generation (RAG) pipelines to complex agentic systems. Own the AI Application Lifecycle: Own the end-to-end lifecycle of AI-powered applications, including system design, development, deployment (CI/CD), monitoring, and optimization in production environments like Databricks and Azure Kubernetes Service (AKS). Optimize RAG Pipelines: Continuously improve retrieval and generation quality through techniques like retrieval optimization (tuning k-values, chunk sizes), using re-rankers, advanced chunking strategies, and prompt engineering for hallucination reduction. Integrate Intelligent Systems: Engineer solutions that seamlessly combine LLMs with our proprietary knowledge repositories, external APIs, and real-time data streams to create powerful copilots and research assistants. Champion LLMOps and Engineering Best Practices: Collaborate with data science and engineering teams to establish and implement best practices for LLMOps, including automated evaluation using frameworks like LLM Judges or MLflow, AI observability, and system monitoring. Evaluate and Implement AI Strategies: Systematically evaluate and apply advanced prompt engineering methods (e.g., Chain-of-Thought, ReAct) and other model interaction techniques to…