AI Engineer

enableIT; Toronto; On-site; CAD 120,000 - 160,000; Full time

Job summary

enableIT is seeking experienced Senior AI Engineers to join our enterprise technology team and build production-ready LLM-powered applications, Agentic AI, and RAG-enabled workflows for customer service and operations.

The role involves designing and deploying AI services on Google Cloud (Vertex AI, BigQuery), implementing MCP interfaces, and establishing robust observability with Langfuse in an Agile environment while mentoring peers.

Qualifications

• 5+ years of professional software development experience.
• 2+ years building Agentic AI or LLM-powered applications.
• Strong Python proficiency and hands-on AI/ML development.
• Experience with LangGraph/LangChain or comparable frameworks.
• Experience with RAG solutions using embeddings and vector search.
• Knowledge of LLM observability, tracing, or monitoring, preferably Langfuse or similar.

Responsibilities

• Design and develop production-grade LLM-powered applications using Python.
• Build AI agents and multi-step AI workflows using LangGraph, LangChain, or similar frameworks.
• Design and implement Retrieval-Augmented Generation (RAG) solutions using enterprise data, embeddings, and vector search.
• Develop and integrate MCP servers and clients to connect AI agents with enterprise tools, data, and services.
• Implement LLM tracing, monitoring, observability, and evaluation using Langfuse or similar platforms.
• Develop and deploy AI services using Google Cloud, including Vertex AI and BigQuery.
• Build RESTful APIs and integrations supporting AI capabilities.
• Implement prompt engineering, tool calling, structured outputs, context management, and guardrails.
• Develop automated unit and integration tests for AI applications and services.
• Evaluate LLM and agent outputs for accuracy, relevance, reliability, and safety.
• Monitor, troubleshoot, and optimize AI applications in production environments.
• Collaborate with product, engineering, architecture, and business teams in an Agile/Scrum environment.
• Contribute to reusable AI engineering patterns, standards, and best practices.
• Participate in architecture discussions, design reviews, and code reviews.
• Mentor other developers and provide technical guidance.
• Stay current with emerging LLM, Agentic AI, and Generative AI technologies.

Skills

Python

Agentic AI

LLM-powered applications

RAG applications

Embeddings

CI/CD practices

Agile/Scrum

Testing

Communication

Tools

LangGraph

LangChain

Langfuse

MCP

Google Cloud

Vertex AI

Vector search

Job description

We are seeking experienced Senior AI Engineers to join a leading enterprise technology team and build reliable, production-ready AI agents and LLM-powered applications.

The ideal candidate will have strong hands-on experience developing Agentic AI, LLM applications, RAG solutions, and AI workflows using Python. You will work with technologies including LangGraph, LangChain, Langfuse, Model Context Protocol (MCP), Google Cloud, Vertex AI, and vector search.

You will collaborate closely with product managers, software engineers, architects, and business stakeholders to deliver practical AI solutions for customer service and enterprise operational use cases.

Key Responsibilities:

• Design and develop production-grade LLM-powered applications using Python.
• Build AI agents and multi-step AI workflows using LangGraph, LangChain, or similar frameworks.
• Design and implement Retrieval-Augmented Generation (RAG) solutions using enterprise data, embeddings, and vector search.
• Develop and integrate MCP servers and clients to connect AI agents with enterprise tools, data, and services.
• Implement LLM tracing, monitoring, observability, and evaluation using Langfuse or similar platforms.
• Develop and deploy AI services using Google Cloud, including Vertex AI and BigQuery.
• Build RESTful APIs and integrations supporting AI capabilities.
• Implement prompt engineering, tool calling, structured outputs, context management, and guardrails.
• Develop automated unit and integration tests for AI applications and services.
• Evaluate LLM and agent outputs for accuracy, relevance, reliability, and safety.
• Monitor, troubleshoot, and optimize AI applications in production environments.
• Collaborate with product, engineering, architecture, and business teams in an Agile/Scrum environment.
• Contribute to reusable AI engineering patterns, standards, and best practices.
• Participate in architecture discussions, design reviews, and code reviews.
• Mentor other developers and provide technical guidance.
• Stay current with emerging LLM, Agentic AI, and Generative AI technologies.

Required Qualifications:

• 5+ years of professional software development experience.
• 2+ years of hands-on experience developing Agentic AI or LLM-powered applications.
• Strong proficiency in Python.
• Hands-on experience building and deploying applications using LLMs.
• Experience with LangGraph, LangChain, or a comparable AI application/agent framework.
• Experience building RAG applications using embeddings and vector search.
• Experience with LLM observability, tracing, or monitoring, preferably Langfuse or a comparable platform.
• Understanding of Model Context Protocol (MCP) and how AI agents interact with enterprise tools and services.
• Experience with Google Cloud, preferably Vertex AI and BigQuery.
• Strong understanding of prompt engineering, tool/function calling, structured outputs, and context management.
• Experience with automated testing, Git, and CI/CD practices.
• Understanding of AI safety, data privacy, responsible AI, and enterprise AI governance.
• Experience working in Agile/Scrum development environments.
• Strong communication and collaboration skills.