About the job
This position is perfect for an engineer who thrives on taking ownership of systems from inception to completion—designing, building, deploying, and managing production-grade AI agents and their supporting backend platforms.
This is a hybrid role based in Toronto.
Your Responsibilities:
- Develop, build, and manage scalable, low-latency backend services and REST APIs that facilitate Generative AI functionalities, including retrieval-augmented generation (RAG) pipelines, vector search, and enterprise-level agentic systems.
- Oversee the entire lifecycle of AI applications and agents, from system architecture and development to CI/CD, deployment, agent evaluation, monitoring, and continuous optimization in production.
- Create production-quality research agents and enterprise AI workflows that seamlessly integrate LLMs with proprietary knowledge, vector databases (e.g., Elasticsearch), internal tools, external APIs, and real-time data.
- Design and manage multi-agent AI systems, including tool-calling agents and agent orchestration patterns, to support intricate research and enterprise workflows.
- Implement AIOps best practices for building, assessing, deploying, and managing AI agents with a strong emphasis on observability, reliability, and quality controls.
- Consistently enhance retrieval and generation quality through prompt engineering, retrieval tuning, re-ranking, advanced chunking strategies, and hallucination mitigation techniques.
- Provide technical leadership through design discussions, code reviews, and mentorship, while collaborating closely with product and business stakeholders to steer the AI roadmap.