Location: Toronto, ON (Hybrid - x3 per week in downtown Toronto office)Type: Full-TimeWe're partnering with a highly technical AI organization building the infrastructure that powers production AI systems at massive scale. Operating as a AI innovation startup within a much larger global technology business, the team combines the pace, ownership, and greenfield engineering opportunities of an early-stage company with the resources and reach of an established platform serving hundreds of millions of users.This is not an AI research role. We're looking for a Staff-level software engineer who can define the architecture and technical direction for large-scale AI infrastructure across inference, agentic systems, distributed platforms, and cloud-native backend services.You'll help build the infrastructure used to deploy and operate text, voice, vision, code, and domain-specific models, while architecting the runtime, orchestration, safety, and developer tooling required for autonomous AI agents to operate reliably in production.This is a highly hands-on Staff position. You'll solve complex engineering problems, lead major technical initiatives, establish platform standards, and influence how production AI systems are built across the organization.What You'll DoDefine the technical architecture and direction for production AI platforms across inference and agentic systemsArchitect and build the runtime, orchestration, and developer tooling required for autonomous AI agentsDesign multi-agent coordination systems that enable agents to reason, collaborate, use tools, and execute complex workflowsBuild multi-model serving infrastructure across text, voice, code, vision, and domain-specific modelsOwn the complete model lifecycle, including deployment, serving, monitoring, updating, routing, and model swappingOptimize inference performance across latency, throughput, reliability, and cost using batching, caching, quantization, and intelligent routingBuild secure tool-use infrastructure that allows agents to interact safely with APIs, databases, and internal servicesDevelop guardrails covering permissioning, sandboxing,



prompt injection, data leakage, and human-in-the-loop oversightBuild evaluation, observability, and monitoring frameworks that measure agent behaviour, detect regressions, and diagnose non-deterministic failuresDesign scalable backend services, APIs, event-driven systems, and durable workflows supporting production AI applicationsDevelop SDKs, APIs, and platform capabilities that allow internal teams to build and deploy AI agents quickly and safelyLead complex, cross-functional technical initiatives in partnership with Product, ML, Infrastructure, and Security teamsEstablish engineering standards and best practices for agent design, model serving, tool calling, evaluation, and production reliabilityMentor senior engineers and raise the technical bar across the broader engineering organizationWhat We're Looking For8+ years of software engineering experience, including significant experience building large-scale backend or distributed systems3+ years of experience building production AI systems, LLM applications, agentic platforms, or machine learning infrastructureDemonstrated experience owning the architecture and delivery of complex, business-critical technical initiativesStrong understanding of LLM-based agent architectures, including tool use, memory, planning, multi-step workflows, and multi-agent coordinationExperience building highly reliable distributed systems using event-driven architectures, task queues, state management, and durable workflowsExperience evaluating production LLM systems, building automated evaluations, detecting regressions, and debugging non-deterministic failuresStrong programming experience with Python and/or TypeScript,



with the ability and willingness to work across bothExperience with Kubernetes, Docker, AWS or GCP, and modern cloud-native deployment practicesExperience working with commercial LLM APIs, open-source models, or model-serving technologiesUnderstanding of inference optimization techniques such as quantization, batching, caching, routing, and GPU utilizationStrong understanding of the security risks associated with agentic systems, including prompt injection, privilege escalation, and data leakageExceptional system-design and software-engineering fundamentalsStrong written and verbal communication skills, with the ability to influence technical direction across teamsComfortable operating in an ambiguous, fast-moving setting with substantial ownership and autonomyPassion for building production software and infrastructure rather than purely research-focused AINice to HaveExperience with model-serving technologies such as vLLM, TensorRT-LLM, or TritonExperience with Temporal, Airflow, Prefect, or similar workflow-orchestration platformsFamiliarity with Model Context Protocol (MCP) or other agent communication standardsExperience with model fine-tuning, LoRA, or quantizationExperience building AI infrastructure within fintech, healthcare, or another regulated industryExperience working with multimodal, voice, or edge-inference systemsExperience designing human-in-the-loop approval and oversight systemsExperience building developer platforms, internal SDKs, or CI/CD automation for AI workloadsWhy Apply?Take Staff-level ownership over the architecture and technical direction of major AI platformsBuild inference and agentic infrastructure used across a global technology organizationWork on genuinely greenfield engineering problems spanning LLMs, autonomous agents, distributed systems, security, and cloud infrastructureRemain deeply hands-on while influencing engineering standards and mentoring a high-calibre technical teamJoin a startup-style environment with significant autonomy, backed by the scale and resources of an established global platform

📌 Staff Ai Engineer (Toronto)
🏢 Arcadia
📍 Toronto