Role overview

Guidepoint is building conversational AI systems that connect to a global network of over 2 million experts through its research platform. As a Senior AI Engineer, you’ll be an early team member on a new initiative, moving working prototypes into production while architecting systems that scale. This is a hands-on role with broad ownership, working closely with product and leadership teams in a hybrid setup at the Toronto office.

Key responsibilities

Build real-time conversational AI agents across voice and chat channels, optimizing for low-latency requirements using modern telephony and media infrastructure.
Design and implement agentic LLM systems that pursue multi-turn conversation goals with behavioral guarantees enforced through code rather than prompts alone.
Manage stateful user sessions that flow seamlessly across communication channels while maintaining context and state.
Connect LLM systems to large internal knowledge assets through retrieval and grounding mechanisms, ensuring structured data flows back into the system.
Develop evaluation infrastructure that measures conversational quality against human baselines and uses metrics to gate production rollouts.
Own services end-to-end including design, implementation, deployment to Kubernetes and Azure, and ongoing operations for latency-sensitive workloads.
Establish engineering patterns and practices for the growing team, including code review standards, observability, and incident response habits.

Requirements

Bachelor’s degree in Computer Science, Engineering, or related technical field with 6+ years of professional software engineering experience; or Master’s degree with 4+ years of professional experience in backend software engineering and Generative AI, including proven ability to design and scale distributed production systems.
At least 2 years building LLM-powered products in production environments, with hands-on experience in orchestration, RAG/grounding, structured outputs, and evaluation-driven iteration.
Strong proficiency in TypeScript or Python, with comfort working across both languages.
Experience with real-time or streaming systems such as WebSockets, WebRTC, audio pipelines, or comparable low-latency work.
Production experience with cloud-native technologies including containers, Kubernetes, CI/CD pipelines, and observability tools; Azure experience is advantageous.
Practical familiarity with agent and LLM frameworks such as LangGraph, LangChain, or CrewAI, and understanding of when to use frameworks versus plain code.
Working knowledge of vector databases and embedding-based retrieval systems.

What makes this role worth considering

You’ll shape the architecture of a new AI initiative from prototype to scale, with significant autonomy and direct influence on product direction. The role combines cutting-edge conversational AI and LLM work with production-grade systems engineering, offering the chance to work across multiple technical domains while building patterns for a growing team.