Senior AI Engineer

It's fun to work in a company where people truly BELIEVE in what they're doing!

Fullsteam is a leading provider of vertical software and embedded payments technology dedicated to helping businesses flourish by providing their customers with seamless experiences. With a dynamic and growing team of over 1,900 employees, we are committed to driving innovation and delivering best-in-class software and payment solutions that empower small and medium-sized businesses across numerous industries. Our purpose is to help our customers grow their businesses and delight their customers. Join us and be a part of a forward-thinking company that values growth, excellence, and the success of our clients.

Commerce7, part of the Fullsteam organization, is a customer centric commerce platform in the alcohol industry. Today we are the platform that powers over 2500 leading alcohol brands including Opus One, Caymus, Harlan Estate, William Chris Winery and more.

We are seeking a Senior AI Engineer to lead the design and development of AI agent capabilities within our platform. In this role, you will own the technical direction for AI, working closely with our product, engineering, DevOps, and QA teams, driving projects independently from concept through to production, and pulling in collaborators at the right stages. Your primary focus will be building agentic systems that help our clients automate day-to-day tasks and access information more intelligently within the platform. You will make foundational architecture decisions, establish engineering standards for AI systems, and deliver scalable, production-ready solutions that have a direct and measurable impact on the clients who use our software. Our stack runs on Node.js and AWS.

Primary Responsibilities:

• Design and implement production-grade agentic systems; autonomous agents that leverage LLMs to reason, use tools, manage context, and orchestrate complex multi-step workflows on behalf of users.
• Build scalable backend services, APIs, and data pipelines that support real-time AI inference, conversation state, and tool execution with robust error handling and recovery.
• Architect systems for scale, designing AI infrastructure that handles growing inference demands, evolving agent complexity, and production reliability requirements.
• Build and maintain RAG pipelines, including embeddings, vector search, and retrieval strategies, to power knowledge-driven features and contextual AI responses.
• Bring foundational ML understanding to inform decisions around model selection, fine-tuning, embeddings, and evaluation and knowing when to use off-the-shelf models versus more custom approaches.
• Collaborate with product, engineering, DevOps, and QA teams to define requirements and deliver AI-powered features, leading technical direction while pulling in the right people at the right stages.
• Evaluate emerging agentic frameworks, LLM providers, and AI tooling; recommend adoptions that move the team’s capabilities forward.
• Establish and document AI engineering standards, covering reliability, safety, observability, and prompt management and building institutional knowledge as the AI function grows.
• Maintain engineering excellence. Write clean, well-tested code; conduct thorough code reviews; champion best practices across the team

Skills & Competencies:

• Strong fundamentals in system design, API design, and distributed systems.
• Clean code practices, SOLID principles, and testable architecture.
• Async programming, concurrency, performance optimization, and caching.
• Database design across relational and vector store paradigms.
• CI/CD, observability, and production operations.
• Agent architecture: orchestration, planning, tool use, and memory management.
• LLM integration: prompt engineering, function calling, and context management.
• RAG pipelines: embeddings, vector search, and retrieval strategies.
• Reliability patterns for non-deterministic AI systems, including guardrails and safety considerations.
• Foundational understanding of ML concepts: training, inference, evaluation, and overfitting/underfitting.
• Familiarity with embeddings and how vector representations work in practice.
• Awareness of when to use off-the-shelf models versus custom training or fine-tuning approaches.

Minimum Qualifications:

• Bachelor’s degree in Computer Science, Engineering, or a related technical field.
• 6+ years of professional software engineering experience.
• 2+ years of hands-on experience designing and building applications that integrate agentic systems in production environments.
• Experience with cloud platforms, preferably AWS (Lambda, Bedrock, OpenSearch).
• Proven track record of shipping and operating production systems with reliability and observability.
• Strong debugging, troubleshooting, and problem-solving skills.
• Ability to work independently with a high degree of ownership, driving projects forward with limited direct oversight.
• Strong communication skills with the ability to collaborate effectively across engineering, product, and non-technical stakeholders.

Salary range: $143,500 - $150,000 CAD

Fullsteam recognizes that your health and wellbeing are a priority. This is why we offer a full suite of benefits that include:
•  Medical
•  Extended Health and LTD plan
•  Dental
•  Vision
•  RRSP (with employer match)
•  Health Spending Account
•  Flexible paid time off

This posting is for an existing vacancy and will remain open until filled.

Fullsteam supports an inclusive workplace that values diversity of thought, experience, and background. Fullsteam is an Equal Opportunity/Affirmative Action employer. All qualified applicants will receive consideration for employment without regard to race, religion, color, national origin, ancestry, age, physical or mental disability, sex, sexual orientation, gender identity/expression, pregnancy, veteran status, marital status, creed, status with regard to public assistance, genetic status or any other status protected by federal, state, or local law.