Staff Engineer / AI Builder

<h3>Accountabilities</h3><li>Design and build agentic AI workflows, including reasoning loops, tool and function calling, orchestration, and single- or multi-agent architectures based on the needs of each use case.</li><li>Develop and maintain production RAG pipelines covering chunking strategies, embeddings, vector search, re-ranking, knowledge freshness, and dynamic content updates.</li><li>Integrate AI solutions with AWS services such as Bedrock and Agent Core, including MCP-based tools and precise tool descriptions that enable reliable orchestration.</li><li>Develop production-grade system prompts using structured role definitions, output constraints, few-shot examples, and other prompt-engineering techniques.</li><li>Build robust evaluation and observability capabilities using golden datasets, LLM-as-judge approaches, RAGAS-style metrics, tracing platforms, and runtime guardrails.</li><li>Design for failure and degradation through retries, backoff and jitter, circuit breakers, fallback models, and clear user-facing recovery experiences.</li><li>Build backend and full-stack services using Python and Node.js, including AWS Lambda, API Gateway, RESTful APIs, and serverless architectures.</li><li>Design DynamoDB single-table schemas for conversation state, agent memory, and session history, while supporting event-driven workflows through Step Functions, SQS, and EventBridge.</li><li>Contribute to frontend integration points, cloud deployment, monitoring, troubleshooting, and production hardening across AWS and Docker-based environments.</li><li>Provide technical leadership by evaluating architectural trade-offs, challenging assumptions, mentoring engineers, and establishing strong practices for agentic AI development.</li><li>Partner with product, design, and delivery stakeholders across global teams to scope, build, launch, and continuously improve AI-powered features.</li><li>Own assigned systems and releases end-to-end, including debugging, reliability improvements, operational support, and maintaining production trustworthiness.</li><h2>Requirements</h2><li>6+ years of professional software engineering experience, including substantial hands-on experience delivering GenAI or LLM-powered systems into production.</li><li>Demonstrated expertise in agentic AI, including reasoning loops, tool/function calling, multi-agent orchestration, and the ability to determine when single-agent or multi-agent architectures are most appropriate.</li><li>Strong practical experience with RAG, including chunking, embeddings, vector databases such as OpenSearch, similarity search, re-ranking, and knowledge-refresh strategies.</li><li>Experience implementing LLM evaluation and observability, including golden datasets, LLM-as-judge, RAGAS or comparable metrics, and tracing platforms such as LangFuse or LangSmith.</li><li>Strong production prompt-engineering capabilities, including the ability to create structured system prompts with meaningful constraints and examples.</li><li>Hands-on experience with the AWS GenAI ecosystem, particularly Bedrock, Agent Core, Lambda, DynamoDB, S3, SQS, EventBridge, and Step Functions.</li><li>Strong Python and Node.js development skills, with experience building full-stack applications and RESTful APIs.</li><li>Solid understanding of reliability patterns for LLM-backed systems, including retries, backoff, circuit breakers, fallback models, and graceful degradation.</li><li>Experience with Docker, cloud-native deployment, production monitoring, and troubleshooting.</li><li>Ability to take ownership of ambiguous, integration-heavy technical problems and communicate architectural decisions with clarity and depth.</li><li>Strong collaboration and communication skills, with the ability to work effectively with product, design, delivery, and engineering teams.</li><li>Experience mentoring engineers and contributing to technical standards and engineering practices.</li><li>Helpful additional experience includes Amazon Bedrock Agent Core, MCP tool integration, agent registration, memory and session management, and gateway provisioning.</li><li>Experience working in regulated or high-stakes environments such as education, healthcare, or financial services is advantageous.</li><li>Familiarity with workflow orchestration and state-machine-based systems, as well as practical experience running LLM observability tooling in production, is a plus.</li><li>A willingness to travel for required business activities and interviews is expected, including approximately 20% travel to the United States.</li><h2>Benefits</h2><li>Competitive salary range of<strong>$176,612–$243,680 CAD</strong>.</li><li>Remote position based in Canada.</li><li>Opportunity to work on production-grade AI systems with significant technical ownership and influence.</li><li>Exposure to advanced agentic AI, GenAI, RAG, AWS, evaluation, and observability technologies.</li><li>Collaborative environment with cross-functional and globally distributed teams.</li><li>Opportunities to mentor engineers and influence engineering standards and architectural direction.</li><li>Work on meaningful enterprise AI solutions where reliability, security, scalability, and measurable impact are core priorities.</li><li>Opportunities for professional growth through challenging technical problems and hands-on exposure to emerging AI technologies.</li><li>Required travel and in-person collaboration opportunities, including final interviews and onboarding as applicable.</li>