Senior AI Engineer

Safe Fleet; Coquitlam; On-site; CAD 120,000 - 135,000; Full time

Job summary

Safe Fleet is seeking a hands-on Senior AI Engineer to build a scalable AI platform with reusable services, agent infrastructure, and governance. You will modernise the AI stack, create automation, and enable engineers to deploy AI capabilities across products.

The role emphasizes internal enablement, security, and maintainability, with a strong focus on AI-native engineering, agentic SDLC, and collaboration with distributed teams. Strong English communication is required.

Qualifications

• 6+ years of professional software engineering experience, with strong system design and software architecture skills.
• Hands-on experience building and deploying AI-powered systems in production.
• Solid command of LLMs and transformer-based models, prompt engineering, RAG architectures, AI agents and workflow orchestration.
• Experience with modern AI platforms and services such as Azure OpenAI, OpenAI, Claude, Google Gemini or equivalent.
• Strong backend and cloud engineering experience, with hands-on Microsoft Azure; AWS or GCP background helpful.
• Practical knowledge of Data Science and Machine Learning fundamentals, including model evaluation and performance trade-offs.
• Proficiency with AI coding agents such as Claude Code, GitHub Copilot, Cursor or equivalent.
• Hands-on experience with AI-Native Engineering and Agentic SDLC — Spec-Driven Development, agent-assisted implementation, automated testing and verification, and development automation.
• Demonstrated ability to enable others — mentoring engineers, writing patterns and documentation used by the team.
• Strong problem-solving and cross-functional collaboration skills, including advanced English for technical discussions with distributed teams.

Responsibilities

• Build the foundation other engineers build on — reusable AI services, agent scaffolding, shared libraries, prompt and context management, and integration patterns for agents.
• Modernise and own SafeFleet’s AI stack: model selection and routing, provider abstraction, cost/governance, and upgrade paths.
• Design and implement RAG architectures, retrieval/indexing pipelines, and data access patterns for agents.
• Build MCP servers and tool integrations that expose internal systems safely to agents.
• Establish AI evaluation, observability and guardrails — eval harnesses, testing, tracing, and cost monitoring in production.
• Develop robust backend services and APIs that enable AI capabilities across teams.
• Mentor the engineering team on AI adoption, set standards, and drive architectural discussions.
• Apply AI-Native Engineering throughout the lifecycle and develop automation and agentic workflows.

Skills

System design

Software architecture

AI production systems

LLMs & prompts

Azure OpenAI

Cloud platforms

AI coding agents

Mentoring engineers

English communication

Job description

Meet The Smart Safety Company

At Safe Fleet our name says it all. We make fleet vehicles – and everyone in and around them – safer. Our fleet safety platform brings together best-in-class products, ground-breaking technology, and a 100-year history of fleet know-how and innovation to solve the world’s biggest fleet safety problems.

About This Role

We are looking for a hands‑on Senior AI Engineer to build the platform that makes that possible — the shared services, agent framework, standards and tooling that allow every engineer on the team to build and operate AI agents of their own.

This is a builder and enabler role, not a research role. You will modernise our AI stack, create reusable AI services and agent infrastructure, automate critical operational workflows, and raise the AI capability of the engineers around you. Success is measured by what the rest of the team can build because of the foundation you put in place.

You will also apply AI‑Native Engineering and Agentic SDLC practices to your own work — using AI coding agents, Spec‑Driven Development and automation to accelerate delivery while holding a high bar for quality, security and maintainability — and establish those practices as the team standard.

From time to time you may contribute to customer‑facing AI capabilities in our product portfolio, but the centre of this role is internal platform, enablement and automation.

Responsibilities

AI Platform and Shared Services

• Build the foundation other engineers build on — reusable AI services, agent scaffolding, shared libraries, prompt and context management, and integration patterns that let the team create agents without reinventing the groundwork.
• Modernise and own SafeFleet’s AI stack: model selection and routing, provider abstraction, cost and token governance, and a clear upgrade path as the technology moves.
• Design and implement RAG architectures, retrieval and indexing pipelines, and the data access patterns agents depend on.
• Build Model Context Protocol (MCP) servers and tool integrations that expose internal systems safely to agents.
• Establish AI evaluation, observability and guardrails — eval harnesses, regression testing for prompts and agents, tracing, quality and cost monitoring in production.
• Develop robust backend services and APIs that make AI capability consumable across teams.

Operational Automation

• Automate critical operational workflows using AI — partnering with teams across Cloud Engineering to identify high‑toil processes and replace them with reliable, auditable agent‑driven automation.
• Build agents and workflows that support areas such as diagnostics, triage, routine remediation, documentation and operational reporting.
• Define governance for autonomous action: guardrails, human‑in‑the‑loop checkpoints, failure modes and auditability.

Enablement and Technical Leadership

• Mentor the engineering team on its AI journey — through pairing, workshops, documented patterns, internal guides and worked examples that move the whole group forward.
• Set AI engineering standards: architecture patterns, prompt and agent design conventions, testing expectations, security and data‑handling practice.
• Lead architecture and design discussions, review AI‑related work, and act as the technical reference point for AI across Cloud Engineering.

AI‑Native Engineering and Agentic SDLC

• Apply AI‑Native Engineering throughout the development lifecycle, using AI coding agents, Spec‑Driven Development and automation to accelerate delivery.
• Build custom AI coding agents, reusable agent skills and automated workflows for implementation, testing, verification, code review and release.
• Integrate agent‑assisted verification into CI/CD, and continuously improve Agentic SDLC practice as a team‑wide standard.

Salary Range: $120,000 - $135,000/yr

• Candidates at the lower end of the range will meet the core qualifications and demonstrate strong potential to grow within the role.
• Mid‑range offers reflect a solid match with the role’s technical and collaborative requirements.
• Offers at the top of the range are reserved for candidates who bring exceptional qualifications, specialized expertise, or unique value that significantly exceeds the baseline expectations.

At Safefleet, we are an equal opportunity employer that is committed to creating a diverse and inclusive workplace where everyone is valued and respected. We embrace diversity and do not discriminate based on race, color, religion, sex, sexual orientation, gender identity, national origin, age, disability, or any other legally protected status. We promote fair and equitable hiring practices and foster a culture of inclusivity and respect. Our core values of integrity, innovation, teamwork, customer focus, and safety guide our efforts to provide a workplace where all employees can thrive and reach their full potential.

Requirements

• 6+ years of professional software engineering experience, with strong system design and software architecture skills.
• Proven hands‑on experience building and deploying AI‑powered systems in production — not prototypes or proofs of concept.
• Solid command of LLMs and transformer‑based models, prompt engineering, RAG architectures, AI agents and workflow orchestration.
• Experience with modern AI platforms and services such as Azure OpenAI, OpenAI, Claude, Google Gemini or equivalent.
• Strong backend and cloud engineering experience, with hands‑on Microsoft Azure — our primary environment. Substantial AWS or GCP background is considered where it transfers.
• Practical knowledge of Data Science and Machine Learning fundamentals, including model evaluation and performance trade‑offs.
• Proficiency with AI coding agents such as Claude Code, GitHub Copilot, Cursor or equivalent, used as part of your daily engineering practice.
• Hands‑on experience with AI‑Native Engineering and Agentic SDLC — Spec‑Driven Development, agent‑assisted implementation, automated testing and verification, and development automation.
• Demonstrated ability to enable others — mentoring engineers, writing the patterns and documentation people actually use, and raising the technical capability of a team.
• Strong problem‑solving, communication and cross‑functional collaboration skills, including advanced English for technical discussion with distributed teams and senior stakeholders.

Preferred

• Experience building reusable AI services, shared AI platforms or internal developer platforms.
• Experience with AI agent orchestration frameworks and production ML pipelines.
• Experience with Model Context Protocol (MCP), local or self‑hosted models, and Hugging Face.
• Experience developing custom AI coding agents, reusable agent skills, automated verification and CI/CD integration.
• Experience applying AI to infrastructure, operations or reliability workflows.
• Experience with Computer Vision, image or video analytics, deep learning or predictive Machine Learning.
• Experience delivering AI‑powered features in commercial software products.
• Familiarity with Agile delivery and experience in regulated or security‑conscious environments.