Staff Full Stack Engineer

Location: Ottawa, ON or Toronto, ON | Hybrid

Type: Permanent | Full-Time

Reports To: Dan Murdock, Director, Engineering

The Role

On a small, high‑velocity Agents team with outsized impact, this role is for a Staff Full Stack Engineer who defines how AI agents operate in product at scale. You provide technical leadership for the systems that enable our AI Agents to reason, act, and deliver value inside our cloud VMS platform, including backend services (TypeScript/Node), agent orchestration frameworks, APIs, tool integrations, and user‑facing workflows.

This is not a feature‑factory role. You will work with other Staff and Senior engineers to define and evolve the execution platform of our agent systems – tool use, workflow coordination, safety boundaries, latency management, and production reliability.

You will have direct access to the latest AI models and tooling, with the autonomy to evaluate emerging technologies and apply them pragmatically where they create measurable product impact.

What You’ll Do

- Aide in the definition and evolution of the architecture for the company's agent platform and orchestration systems
- Design and implement production‑grade agent services in TypeScript/Node
- Design scalable APIs and platform capabilities that enable teams across the organization to build on agent infrastructure
- Establish patterns and frameworks for integrating LLM/VLM systems with internal tools, permissions, and data sources
- Establish and enforce safety, guardrails, and failure handling in agent execution paths
- Optimize latency, reliability, and scalability of agent‑facing services in AWS/EKS
- Drive observability strategy including tracing, debugging, performance analysis and operational metrics
- Mentor engineers, raise engineering standards,



and partner with Staff team members to influence technical direction across teams
- Operate in tight feedback loops, shipping working code and validating ideas quickly

What You Bring (Must‑Have)

- Extensive experience building and operating production systems with TypeScript and Node.js
- Experience integrating LLMs / VLMs into production workflows
- Deep experience designing distributed systems with solid understanding of reliability, scalability, fault tolerance, and operational excellence
- Experience architecting and operating cloud‑native systems in AWS (EKS preferred)
- Experience instrumenting systems for observability and debugging (OpenTelemetry or similar)
- Track record of influencing architecture, engineering practices, and technical direction beyond a single team
- Ability to navigate ambiguity, make pragmatic tradeoffs, and drive execution from concept through production
- Experience mentoring senior engineers

Nice‑to‑Have

- Experience designing or leading development of AI agent platforms, orchestration frameworks, or tool‑use systems
- Experience implementing AI safety controls, governance, and guardrails around model execution
- Experience designing event‑driven, workflow‑based, or distributed orchestration architectures
- Experience working in a small, high‑velocity startup or AI‑first environment

Security Requirements

- Candidates must undergo a criminal records check upon hire
- Be a Canadian Citizen (dual citizens included), or eligible to work in Canada
- Be willing to comply with the company's own security policies and standards

Equal Opportunity Employer

The company is an Equal Opportunity Employer. We’re committed to building a diverse and inclusive workplace. If you require accommodation during the selection process, please let us know.

Compensation Range: CA$138,445 - CA$185,000

#J-18808-Ljbffr

📌 Staff Full Stack Engineer (Toronto)
🏢 United States Digital Space
📍 Toronto