Senior AI Engineer

Fullsteam•Area B (Goat River Valley), BC

2d•CA$143,500 - CA$150,000

About The Position

Fullsteam, through its organization Commerce7, is seeking a Senior AI Engineer to lead the design and development of AI agent capabilities within their platform. This role involves owning the technical direction for AI, collaborating with product, engineering, DevOps, and QA teams, and independently driving projects from concept to production. The primary focus is on building agentic systems to help clients automate tasks and access information more intelligently. The engineer will make foundational architecture decisions, establish AI engineering standards, and deliver scalable, production-ready solutions. The technology stack runs on Node.js and AWS.

Requirements

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.
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.

Responsibilities

Design and implement production-grade agentic systems, including autonomous agents that leverage LLMs for reasoning, tool use, context management, and orchestrating multi-step workflows.
Build scalable backend services, APIs, and data pipelines to support real-time AI inference, conversation state, and tool execution with robust error handling.
Architect systems for scale, designing AI infrastructure to handle 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.
Apply foundational ML understanding to inform decisions on model selection, fine-tuning, embeddings, and evaluation, determining when to use off-the-shelf models versus custom approaches.
Collaborate with product, engineering, DevOps, and QA teams to define requirements and deliver AI-powered features, leading technical direction.
Evaluate emerging agentic frameworks, LLM providers, and AI tooling, recommending adoptions to advance the team's capabilities.
Establish and document AI engineering standards for reliability, safety, observability, and prompt management, building institutional knowledge.
Maintain engineering excellence by writing clean, well-tested code, conducting thorough code reviews, and championing best practices.