Senior Software Engineer – AI – Quebec

Webhosting; Quebec; On-site; CAD 90,000 - 120,000; Full time

Job summary

Webhosting seeks a Senior Applied AI Engineer who blends software engineering with practical AI problem solving to build production AI experiences across Network Solutions.

You will evaluate customer and product problems, select the strongest approach, and ship reliable, observable production systems that are secure and cost-efficient.

Qualifications

• Translate loosely defined product problems into practical AI solutions.
• Design and build production AI services using Python and modern stacks.
• Build reliable tool calling agents and multi-step workflows.

Responsibilities

• Translate product problems into practical AI solutions and choose between LLMs, RAG, tool calling, agents, deterministic workflows, or traditional software.
• Design event-driven systems with message queues and retries.
• Build and improve RAG systems for ingestion, embeddings, and retrieval.

Skills

LLMs

RAG

Tool calling

Agents

Software engineering

Prompting

Context management

Model routing

Streaming responses

Tools

Docker

CI/CD

OpenTelemetry

Langfuse

Kubernetes

Azure

pgvector

Semantic Kernel

LangGraph

PydanticAI

Job description

What you’ll do & how you’ll make your mark .

We are looking for a hand on Senior Applied AI Engineer who combines strong software engineering with practical AI problem solving. You will build production AI experiences across Network Solutions, including conversational agents, business and website creation, knowledge and FAQ agents, content experiences, domain discovery, and intelligent automation.

You will take ambiguous customer and product problems, evaluate different approaches, and independently turn the strongest solution into reliable, secure, observable, and cost-efficient production systems. This is an applied engineering role focused on shipping real AI products.

Who you are & what you’ll need to succeed

• Translate loosely defined product problems into practical AI solutions, choosing between LLMs, RAG, tool calling, agents, deterministic workflows, or traditional software.

Design and build production AI services using Python, FastAPI, asynchronous workers, PostgreSQL, Redis, queues, model APIs, and external tools.

Build reliable tool calling agents and multi step workflows that interact with internal APIs, MCP tools, business systems, and knowledge sources.

Design event driven systems using RabbitMQ, Kafka, Azure Service Bus, or equivalent platforms, including retries, dead letter handling, idempotency, back pressure, and failure recovery.

Build and improve RAG systems covering ingestion, chunking, embeddings, hybrid retrieval, reranking, metadata filtering, context construction, and citations.

Experiment with models from OpenAI, Anthropic, Google, xAI, and open weight ecosystems, selecting the right model for quality, latency, reliability, and cost.

Create AI evaluation pipelines using curated datasets, regression tests, retrieval metrics, LLM as judge techniques, groundedness checks, and tool execution evaluation.

Diagnose hallucinations, retrieval failures, incorrect tool usage, agent loops, latency issues, provider failures, and unexpected inference costs.

Operate as an AI powered engineer using Cursor, Claude Code, OpenAI Codex, or equivalent coding agents to accelerate design, implementation, testing, debugging, and refactoring.

You should be comfortable going beyond a working demo and understand how modern AI systems behave, fail, and scale in production.

Strong understanding of prompting, structured outputs, tool schemas, context management, model routing, retries, fallbacks, rate limits, and streaming responses.

Ability to design experiments and evaluations that compare approaches using measurable outcomes rather than subjective testing alone.

Understanding of retrieval quality, grounding, hallucination mitigation, prompt injection risks, tool authorization, and practical agent guardrails.

Experience with Docker, CI/CD, automated testing, observability, distributed tracing, OpenTelemetry, Langfuse, or similar tooling.

How you’ll work

You will often start with an ambiguous customer or product goal rather than a detailed implementation plan. You should be able to independently break the problem down, validate assumptions, choose an approach, and drive the solution through production.

Turn product goals into testable technical hypotheses and rapidly prototype alternatives when needed.

Choose the simplest architecture that solves the problem well rather than using an agent or LLM by default.

Define quality, latency, reliability, safety, and cost targets and measure production performance against them.

Own implementation across APIs, workflows, data, queues, model integration, evaluations, observability, and production support.

Use AI coding agents aggressively to increase engineering velocity while preserving architecture quality, testing discipline, security, and maintainability.

What will make you stand out

Experience with Semantic Kernel, Microsoft Agent Framework, LangGraph, PydanticAI, or equivalent agent frameworks.

Experience building or consuming Model Context Protocol tools and servers, or working with model gateways such as LiteLLM.

Experience with Azure AI Search, pgvector, Chroma, Kubernetes, Azure, OCI, or similar production AI platform technologies.

Experience building high scale customer facing AI products, open weight model inference, AI safety controls, or automated agent evaluation systems.

Strong problem solving, excellent engineering judgment, and the ability to independently move from ambiguity to a production quality solution are the foundation for this role.

Join us to build the agent-powered backbone of our AI platform-robust, model agnostic, and ready for millions of users.

This Job Description includes the essential job functions required to perform the job described above, as well as additional duties and responsibilities. This Job Description is not an exhaustive list of all functions that the employee performing this job may be required to perform. The Company reserves the right to revise the Job Description at any time, and to require the employee to perform functions in addition to those listed above.