This list contains only the countries for which job offers have been published in the selected language (e.g., in the French version, only job offers written in French are displayed, and in the English version, only those in English).
Guidepoint is seeking an AI Engineer II to join our Toronto-based AI team. The Toronto Technology Hub is home to our AI/ML and Data organization, focused on building a modern, responsible AI platform that powers Guidepoint’s research enablement products and enterprise intelligence. In this role, you will build and operate AI systems and agents that support compliance, editorial workflows, and intelligent automation. You will work hands-on with Generative AI agents, production-grade APIs, and scalable data pipelines, contributing to their reliability, quality, and long-term operation in production.
Job Responsibility:
Design and implement AI systems and agents that automate compliance and editorial workflows in support of research enablement
Design and implement agent workflows using frameworks such as LangGraph and LangChain
Build agents that perform intent interpretation, task decomposition, tool use, web search, and human-in-the-loop escalation
Build and operate production-grade REST APIs to serve AI and agent capabilities
Develop and maintain scalable data pipelines and background workers that support AI workloads and agent execution
Design and maintain retrieval-augmented generation (RAG) pipelines using embeddings, Elasticsearch, structured data, and web-based sources
Develop and maintain automated evaluation pipelines for agent behavior and outputs using MLflow and related tooling
Improve agent reliability, latency, and cost through prompt engineering, prompt management techniques, and workflow optimization
Integrate agents with internal services, APIs, data stores, and asynchronous workers using queues such as RabbitMQ or Redis
Monitor and operate agent systems using observability platforms such as Datadog, including alerting and incident response
Debug and mitigate agent failure modes such as hallucinations, tool misuse, and state or orchestration errors
Manage the full lifecycle of agent systems and supporting APIs, from implementation through deployment and long-term operation using CI/CD pipelines and Kubernetes
Requirements:
3–5 years of professional experience designing, building, and operating production-grade backend systems
2+ years of hands-on experience building and operating Generative AI and agent systems in production
Strong Python engineering skills, with experience building scalable REST APIs using frameworks such as FastAPI
Working knowledge of JavaScript and Node.js
Hands-on experience building and maintaining agent-based AI systems in production using frameworks such as LangChain or LangGraph
Experience working with large language models from providers such as OpenAI, Anthropic, or Google Gemini, including prompt engineering and tool integration
Practical experience building and operating RAG systems using embeddings and retrieval systems such as Elasticsearch
Experience evaluating AI or agent systems beyond manual testing, including automated or programmatic evaluation using tools such as MLflow
Familiarity with asynchronous processing and workers using technologies such as RabbitMQ or Redis
Experience with monitoring, alerting, deployment, and CI/CD pipelines in cloud-native environments using Kubernetes
Comfortable owning systems independently, including debugging, on-call support, and iterative improvement in production
What we offer:
Paid Time Off
Comprehensive benefits plan
Company RRSP Match
Development opportunities through the LinkedIn Learning platform