AI Engineer

Ian Martin Group; Brampton, Toronto; On-site; CAD 116,000 - 121,000; Full time

Job summary

Ian Martin Group is hiring an AI Engineer to join a client team in Brampton/Toronto, Ontario. The role focuses on building reliable AI agents and workflows powered by LLMs, using Python, LangGraph, Langfuse, MCP, and Google Cloud.

The ideal candidate has extensive Python experience, hands-on LLM work, and familiarity with LangGraph, LangChain, and cloud AI services. Hybrid/onsite collaboration with cross-functional teams is expected.

Qualifications

• 5+ years of professional software development experience.
• 2+ years developing agentic AI or LLM-powered applications.
• Strong Python development experience; hands-on with LLMs.

Responsibilities

• Design and develop LLM-powered applications using Python.
• Build AI agents and workflows using LangGraph.
• Develop RAG solutions using embeddings and vector search.
• Connect AI agents to tools via MCP servers.
• Implement LLM tracing, monitoring, and evaluation with Langfuse.
• Deploy AI services on Google Cloud.
• Create APIs and integrations for AI capabilities.
• Write unit and integration tests; ensure quality.

Skills

Python

LLM development

LangGraph/LangChain

LLM observability

Google Cloud

RESTful APIs

Agile

CI/CD

Testing

Education

Bachelor's or Master's in CS / related field

Tools

LangGraph

LangChain

Langfuse

MCP

Vertex AI

BigQuery

Pinecone

Docker

Pub/Sub

Job description

AI Engineer

• Pay Rate: $56.56/hour, depending on experience
• Contract Length: 6 Months, with a strong likelihood of extension
• Location: Brampton or Toronto, Ontario

Raise is currently hiring an AI Engineer on behalf of our client. They’re expanding their team to meet growing needs, making this a unique opportunity to work with an industry leader. Our Client is a technology company that combines decades of industry expertise with next-generation AI technology that helps organizations reinvent how they build, operate and deliver by pairing human ingenuity with agentic systems that scale intelligence across the enterprise.

Note: The primary pay rate is based on T4 classification; however, we will also consider applications from candidates interested in an INC classification, where applicable.

Description

The ideal candidate will be passionate about building reliable and practical AI agents and AI workflows powered by Large Language Models (LLMs). You will use Python, LangGraph, Langfuse, Model Context Protocol (MCP), and Google Cloud to develop AI agents, Retrieval-Augmented Generation (RAG) solutions, and production-ready AI services. You will work in a fast-paced organization using Agile/Scrum methodologies and collaborate with product managers, software engineers, and business stakeholders to deliver AI solutions for customer service and operational requirements.

Responsibilities

• Design and develop LLM-powered applications using Python
• Build AI agents and workflows using LangGraph
• Develop RAG solutions using enterprise data, embeddings, and vector search
• Build and integrate MCP servers to connect AI agents with enterprise tools, data, and services
• Implement LLM tracing, monitoring, and evaluation using Langfuse
• Develop and deploy AI services on Google Cloud
• Create APIs and integrations for AI capabilities
• Write unit and integration tests to ensure solution quality
• Evaluate AI outputs for accuracy, relevance, reliability, and safety
• Monitor and troubleshoot AI applications in production
• Collaborate with product, engineering, architecture, and business teams
• Contribute to AI engineering standards and reusable development patterns
• Mentor developers and provide guidance through design and code reviews
• Remain current with developments in LLMs and generative AI

Qualifications

• 5+ years of professional software development experience
• 2+ years of experience developing agentic AI or LLM-powered applications
• Strong Python development experience
• Hands-on experience building applications with LLMs
• Experience with LangGraph, LangChain, or a similar AI application framework
• Experience with Langfuse or another LLM observability platform
• Understanding of Model Context Protocol (MCP) and its use in connecting AI agents with tools and enterprise systems
• Experience with Google Cloud services such as Vertex AI and BigQuery
• Experience building RAG solutions using embeddings and vector search
• Experience developing RESTful APIs using FastAPI, Flask, or a similar framework
• Understanding of prompt engineering, tool calling, structured outputs, and context management
• Experience with automated testing, Git, and CI/CD practices
• Understanding of data privacy, AI safety, and responsible AI principles
• Experience working with Agile methodologies
• Excellent verbal and written communication skills
• Desirable Skills and Experience
• Hands-on experience developing or integrating MCP servers and clients
• Experience with Gemini, OpenAI, Anthropic, or open-source LLMs
• Experience with vector databases such as Vertex AI Vector Search, Pinecone, pgvector, or Supabase
• Experience with Docker and containerized deployments
• Familiarity with event-driven systems such as Pub/Sub
• Familiarity with LLM evaluation frameworks
• Experience working with high-traffic enterprise applications
• Experience in retail, e-commerce, loyalty, customer service, or supply-chain environments
• Experience with collaboration tools such as JIRA and Confluence
• Personal Skills & Qualities
• Self-motivated with a strong team spirit
• Strong problem-solving and troubleshooting skills
• Ability to work independently and collaborate effectively within a team
• Comfortable working with evolving requirements and technologies
• Strong sense of ownership and accountability
• Ability to manage multiple priorities in a fast-paced environment
• Ability to communicate AI concepts to technical and non-technical stakeholders
• Commitment to building reliable, secure, and responsible AI solutions
• Education and Certifications
• Bachelor's or Master's degree in Computer Science, Software Engineering, Artificial Intelligence, Data Science, or a related quantitative field. Or equivalent practical experience (5+ years of professional software engineering) combined with a proven track record of deploying production-ready AI applications.
• Recommended Certifications Google Cloud Professional Certifications, Google Cloud Certified Professional Cloud Architect or Google Cloud Certified Professional Data Engineer, AI & Machine Learning Certifications

Additional Information

Candiates will be working a hybrid schedule of 4 days per week a t the clients Toronto Downtown site or the clients Brampton site

Looking for meaningful work? We can help!

Raise is an established hiring firm with over 65 years of experience. We believe strongly in making the world a better place through work, which is why we’re a certified B Corporation and donate 10% of our profits to charity.

We strive to build teams that reflect the diversity of the communities we work in. We encourage all qualified applicants to apply, including people from traditionally underrepresented groups such as women, visible minorities, Indigenous peoples, people identifying as LGBTQ2SI, veterans, and people with visible/nonvisible disabilities.

We have a dedicated webpage for accommodations where you can learn more about what we offer and request accommodation: https://raise.jobs/accommodations/

In order to submit candidates for roles, our clients will sometimes require personal information to confirm the identity of applicants and their legal status to work. Raise will never ask you for personal or banking information unless you have been selected for a job. If you are ever unsure about the legitimacy of this or any other Raise job posting (or have any other questions), please contact us at [phone] or [e-mail].

#WES

#LI-SC1