Lead AI Engineer

About You

• You’ve built and deployed production-grade LLM systems and want to own foundational AI architecture in a true 0->1 environment.
• You thrive in fast-moving startup environments and enjoy solving complex problems around AI safety, reliability, and scalability.
• You’re excited by the opportunity to build technology that can have a real-world impact within clinical mental health and therapy environments.

About Our Client

• Our client is a stealth AI health tech company building next-generation AI systems focused on clinical mental health therapy and patient support.
• Backed by experienced operators, they are building highly responsible AI infrastructure designed for high-trust and highly sensitive environments.
• This is an opportunity to join early and help shape the product, architecture, and engineering culture from the ground up.

Responsibilities

• Design, build, and deploy production LLM systems across core platform and therapy workflows.
• Own AI safety systems, deterministic enforcement layers, and guardrail architecture.
• Build and maintain scalable RAG pipelines, evaluation frameworks, and monitoring systems.
• Design agentic and multi-step AI workflows with strong human escalation and review systems.
• Define LLM evaluation metrics, failure thresholds, hallucination mitigation systems, and output validation frameworks.
• Develop backend services, APIs, orchestration layers, and platform infrastructure primarily in Python.
• Build systems focused on audit logging, traceability, compliance, and secure handling of highly sensitive user data.
• Partner closely with leadership, product, and clinical stakeholders on technical direction and roadmap planning.
• Operate independently while helping establish engineering standards and best practices within a high-growth startup environment.

Qualifications

• Experience building and deploying production LLM systems.
• Experience designing AI safety and guardrail systems.
• Experience with agentic or multi-step AI workflows.
• Experience owning RAG architecture and evaluation pipelines.
• Experience implementing deterministic enforcement or output validation systems.
• Experience working within regulated or highly sensitive environments including healthcare, fintech, legal, security, or trust & safety.
• Experience defining LLM evaluation metrics, monitoring systems, and failure thresholds.
• Experience building human-in-the-loop or escalation workflows.
• Strong backend engineering experience with Python and API development.
• Strong system design and architecture ownership experience.
• Experience handling sensitive user data or high-risk user interactions.
• Experience with audit logging, traceability, and compliance-focused systems.
• Experience mitigating unsafe outputs, hallucinations, and prompt injection risks.
• Ability to operate independently within a 0→1 startup environment.

Compensation Range

• Up to $250,000 CAD base salary.
• Meaningful early-stage equity package.
• Fully remote across Canada.
• Opportunity to build foundational AI systems with massive real-world impact.