Noibu is the leading ecommerce analytics & monitoring platform, purpose-built to help retailers protect and grow online revenue. By unifying site monitoring, experience analytics, and conversion growth opportunities in a single pane of glass, Noibu captures the most important end-to-end shopping data, without the complexity of traditional analytics tools.

Noibu surfaces critical site errors, performance issues, and customer journey friction that block conversions, then ties every insight directly to business impact, session replays, and full technical context. This makes it easy for ecommerce teams to understand why things are happening and what to prioritize, without dedicated analytics headcount.

The result: faster decisions, better collaboration across teams, optimized customer experiences, and revenue growth.

Learn more about Noibu at www.noibu.com.

About the Team and Role

We're building AI-powered capabilities into Noibu's platform to help ecommerce teams move faster, surface insights automatically, and resolve issues before they cost revenue. This role sits at the intersection of software engineering and applied AI, with a focus on building production-grade agentic systems, RAG pipelines, and LLM-driven workflows using our core stack (LangGraph, LangChain, LangSmith). You'll own the technical direction of AI initiatives, ship features that customers use daily, and help establish AI engineering as a core discipline at Noibu.

What You'll Do

Design and build production AI systems — architect autonomous agents, multi-agent orchestration workflows, and retrieval-augmented generation (RAG) pipelines that ship to real users
Build agentic workflows with LangGraph — implement stateful, multi-step agent workflows including tool use, error recovery, human-in-the-loop patterns, and conditional branching
Integrate LLMs into the product — connect to models from OpenAI, Anthropic, Gemini and open-source providers using clean integration patterns (stable interfaces, structured outputs, and function/tool calling)
Own production reliability — manage prompt versioning, trace logging (LangSmith), evaluation pipelines, regression testing, and observability for all AI systems
Shape AI strategy — evaluate emerging models, frameworks, and techniques; make pragmatic build-vs-buy decisions; define and track AI performance metrics (latency, cost-per-query, retrieval accuracy, agent success rates)
Collaborate cross-functionally — partner with Product, Design, and customer-facing teams to identify high-impact AI use cases that solve real customer pain points
Mentor and lead — raise the AI literacy of the engineering org through code reviews, tech talks, documentation, and hands-on guidance

What You Bring

5+ years of professional software engineering experience, with at least 2 years focused on AI/ML or LLM application development
Hands-on production experience with LangGraph, or comparable agentic AI frameworks
Strong Python proficiency with clean, testable code practices
Experience building and deploying RAG systems, including vector databases, embedding models, retrieval strategies, and re-ranking
Deep understanding of LLM APIs (OpenAI, Anthropic, Gemini, open-source), including function calling, structured outputs, streaming, prompt/context engineering, and token management
Experience putting AI systems into production with proper monitoring, evaluation, and observability (e.g., LangSmith, custom eval pipelines)
Strong software engineering fundamentals: version control, CI/CD, testing, code review, and system design
Knowledge of prompt engineering best practices, including chain-of-thought, few-shot, and structured output techniques

Nice to Have

Experience with multi-agent systems and orchestration patterns (supervisor, hierarchical, or collaborative agent architectures)
Familiarity with model fine-tuning, RLHF, or parameter-efficient training methods (QLoRA, LoRA)
Experience with MLOps tooling: experiment tracking (MLflow, W&B), model serving, containerization (Docker, Kubernetes)
Contributions to open-source AI projects or published work in applied AI
Experience in ecommerce, web performance monitoring, or developer tooling domains

Who You Are

You're a builder who ships — you care more about getting AI into users' hands than chasing theoretical perfection
You stay current in a fast-moving landscape and bring new ideas to the team, but you're pragmatic about what to adopt vs. what to watch
You communicate complex AI concepts clearly to non-technical stakeholders
You thrive in cross-functional collaboration and genuinely enjoy understanding customer problems
You mentor others generously and believe in raising the whole team's capabilities

125000 - 175000 CAD a year