Staff AI Builder

Role overview Staff-level engineer role focused on leading the design and delivery of production AI and machine learning systems. The position combines hands-on architecture work with technical leadership across a cross-functional team, owning systems end-to-end where reliability, security, and scalability matter. Work centers on real, in-flight agentic and generative AI products rather than prototypes.

Responsibilities - Design and build agentic workflows, including reasoning loops, tool and function calling, and single- and multi-agent orchestration patterns - Build and maintain retrieval-augmented generation pipelines covering chunking, embeddings, vector search, re-ranking, and freshness handling for dynamic knowledge sources - Integrate with managed GenAI platforms and agent frameworks, including MCP-based tool design and precise tool descriptions for orchestrator routing - Author and iterate production system prompts with structured role framing, output constraints, and few-shot design - Embed evaluation and observability into shipped agents through golden datasets, RAGAS-style metrics, LLM-as-judge guardrails, and tracing tooling - Engineer for LLM failure modes, including retries with backoff and jitter, circuit breakers, fallback models, and clear user-facing degradation paths - Build backend services in Python and Node.js across serverless architectures, including RESTful APIs and event-driven orchestration for asynchronous agent operations - Design single-table schemas for conversation state, agent memory, and session history, with attention to transactional integrity - Contribute to deployment, monitoring, and production troubleshooting in cloud-native environments using containers and managed cloud services - Bring informed technical judgment to architecture discussions, mentor other engineers, and own assigned features end-to-end

Requirements - Six or more years of professional software engineering experience, including meaningful production GenAI or LLM-powered work - Hands-on depth in agentic AI, including reasoning loops, tool calling, multi-agent orchestration, and a considered view on single- versus multi-agent trade-offs - Practical retrieval-augmented generation expertise across chunking strategies, embeddings, vector databases, similarity search, and re-ranking - Experience building evaluation and observability for LLM systems using golden datasets, LLM-as-judge approaches, RAGAS or comparable metrics, and tracing tools - Strong prompt engineering skills with the ability to write structured production prompts under real constraints - Hands-on experience with the AWS GenAI stack, including Bedrock, Lambda, DynamoDB single-table design, S3, SQS, EventBridge, and Step Functions - Strong Python and Node.js skills with full-stack and RESTful API experience - Solid grasp of production reliability patterns for LLM-backed systems, including retries, backoff, circuit breakers, and fallback models - Comfort with containerization and cloud-native deployment, plus the ability to navigate ambiguous integration-heavy problems

Nice to have - Direct experience with Amazon Bedrock Agent Core, including agent registration, MCP tool wiring, memory and session management, and gateway provisioning - Background in regulated or high-stakes domains such as education, healthcare, or financial services where evaluation rigor carries real consequences - Familiarity with workflow orchestration tools such as Step Functions, Sequencer, or similar state-machine systems - A grounded point of view on LLM observability tooling shaped by actual production use

Benefits and work setup - Salary range listed as 176,612 to 243,680 CAD