Role overview

Guidepoint is building production AI systems to enhance its research platform, combining multi-agent workflows, conversational AI, and retrieval technology. As a Senior AI Engineer, you will take working prototypes into production, establish system architecture, and work across agent design, evaluation, APIs, and cloud deployment while collaborating with product, engineering, and compliance teams. This hybrid position is based in Toronto, Ontario.

Key responsibilities

Design and deploy multi-agent workflows where specialized agents collaborate on research tasks, including task planning, tool use, delegation, and result synthesis.
Enforce permissions, domain rules, and safety requirements in application code, implementing safe tool use, clear failure handling, and human review mechanisms.
Build reliable multi-turn workflows with explicit state management, memory strategies, timeouts, retries, and recovery from partial failures.
Develop and maintain Python services and APIs that connect agents to Guidepoint products, internal data systems, and third-party providers.
Construct retrieval and search pipelines over large internal knowledge assets to return structured, traceable results with clear source attribution.
Define and maintain evaluation systems measuring task success, factual accuracy, groundedness, policy adherence, latency, and cost using representative test sets and production feedback.
Own AI services from design through production deployment and operations using containers, Kubernetes, Azure, and Databricks, and establish engineering practices for code review, testing, and observability as the team expands.

Requirements

Bachelor’s degree in Computer Science, Engineering, or related technical field with 6+ years of professional experience; or Master’s degree with 4+ years of professional experience in backend software engineering and Generative AI.
Minimum 8+ years of software engineering experience, including 3+ years building and operating production AI or LLM-powered products.
Proven track record designing, building, and scaling distributed, production-grade systems with demonstrated experience shipping multi-agent or agentic workflows in production.
Strong Python skills and experience building production APIs and backend services, with TypeScript experience helpful.
Hands-on experience with cloud-native deployment including containers, Kubernetes, CI/CD, and production observability.
Production experience with Azure and/or Databricks, practical LLM evaluation skills, and familiarity with retrieval-augmented generation, embeddings, and vector databases.
Understanding of model and workflow risks including unsupported answers, prompt injection, and unsafe tool calls, with experience addressing them through system design.

What makes this role worth considering

You will have broad ownership of a critical system supporting a global research platform backed by over 2 million experts. The role offers the opportunity to shape architecture and establish engineering practices as the team grows, working on high-impact applied AI systems that combine multiple advanced techniques in a production environment.