AI Engineer

Guidepoint•Toronto, ON

7d•CA$135,000 - CA$210,000•Hybrid

About The Position

Guidepoint seeks an experienced AI Engineer to join its Toronto-based AI team. This role is crucial for building a modern data infrastructure for advanced analytics and responsible AI development. The position focuses on creating cutting-edge Generative AI and analytical capabilities to enhance Guidepoint’s research enablement platform and data products. The AI Engineer will lead the development and scaling of Generative AI systems, including LLM applications and research agents, while integrating responsible AI principles and MLOps best practices. This role will be a key contributor to building scalable AI/ML capabilities using Databricks and other advanced tools across Guidepoint’s products. Guidepoint’s Technology team is dedicated to problem-solving and improving user experience through internal application architecture enhancements and new AI-enabled products. This is a hybrid position based in Toronto.

Requirements

Bachelor’s degree in Computer Science, Engineering, or a related technical field with 6+ years of professional experience; or a Master’s degree with 4+ years of professional experience in backend software engineering and Generative AI.
Proven track record of designing, building, and scaling distributed, production-grade systems.
Deep expertise in Python, a major backend framework (e.g., FastAPI, Flask), and asynchronous programming (e.g., asyncio).
Proficiency in designing RESTful APIs, microservices, and managing the complete operational lifecycle (testing, CI/CD, observability, monitoring, alerting, high uptime, zero-downtime deployments).
Hands-on experience deploying and managing applications on a major cloud platform (Azure preferred) using containerization (Docker) and orchestration (Kubernetes, Helm).
2+ years of experience building applications leveraging large language models (OpenAI, Anthropic, Google Gemini).
Direct experience with modern LLM patterns such as retrieval-augmented generation (RAG), hybrid search using vector databases (Pinecone, Elasticsearch), multi-agent AI systems with tool calls, and prompt engineering.
Experience designing and implementing robust evaluation frameworks for LLM-based systems (rubric-based scoring, LLM Judges, MLflow) and monitoring for performance and drift.
Familiarity with large-scale data processing platforms and tools (e.g., Databricks, Apache Spark).
Practical experience with libraries and frameworks like LangChain or LlamaIndex for building LLM-powered applications.
Demonstrated ability to lead complex technical projects and foster the growth of other engineers.

Responsibilities

Architect and build scalable, low-latency backend services and APIs for Generative AI features, including RAG pipelines and agentic systems.
Manage the end-to-end lifecycle of AI-powered applications: system design, development, deployment (CI/CD), monitoring, and optimization on platforms like Databricks and Azure Kubernetes Service (AKS).
Optimize RAG pipelines by improving retrieval and generation quality through techniques such as tuning k-values, chunk sizes, using re-rankers, advanced chunking strategies, and prompt engineering for hallucination reduction.
Engineer solutions that integrate LLMs with proprietary knowledge repositories, external APIs, and real-time data streams to create copilots and research assistants.
Establish and implement best practices for LLMOps, including automated evaluation (LLM Judges, MLflow), AI observability, and system monitoring, in collaboration with data science and engineering teams.
Evaluate and apply advanced prompt engineering methods (e.g., Chain-of-Thought, ReAct) and other model interaction techniques to optimize LLM performance and safety.
Provide technical leadership to junior engineers through code reviews, mentorship, and design discussions.
Collaborate with product and business stakeholders to translate user needs into technical requirements, define priorities, and influence the AI product roadmap.