Staff AI Builder

Location: Remote in Canada

Salary: CAD 176,612–243,680 annually

Company

Robots & Pencils designs and delivers production-ready AI systems that integrate into enterprise operations and real-world workflows.

What you will do

• Design and build agentic workflows, including reasoning loops, tool/function calling, and single- or multi-agent orchestration.
• Build RAG pipelines covering chunking, embeddings, OpenSearch vector search, re-ranking, and knowledge refresh handling.
• Integrate AWS Bedrock, Agent Core, and MCP-based tools; develop structured production prompts.
• Implement LLM evaluation and observability with golden datasets, RAGAS-style metrics, LLM-as-judge, and tracing.
• Build Python and Node.js backend services, serverless AWS architectures, DynamoDB schemas, and event-driven workflows.
• Own features and releases through debugging, hardening, deployment, monitoring, mentoring, and production troubleshooting.

Requirements

• 6+ years of professional software engineering experience, including meaningful experience shipping GenAI/LLM-powered systems in production.
• Hands-on expertise in agentic AI, including reasoning loops, tool/function calling, multi-agent orchestration, and judgment on single-agent versus multi-agent designs.
• Practical RAG experience with chunking strategies, embeddings, vector databases such as OpenSearch, cosine similarity search, and re-ranking.
• Experience building LLM evaluation and observability with golden datasets, LLM-as-judge, RAGAS or comparable metrics, and LangFuse, LangSmith, or equivalent tracing tools.
• Strong prompt engineering skills, including production system prompts with structured roles, constraints, and few-shot design.
• Hands-on AWS GenAI experience with Bedrock, Agent Core, Lambda, DynamoDB single-table design, S3, SQS, EventBridge, and Step Functions.
• Strong Python and Node.js skills, including full-stack applications and RESTful APIs.
• Understanding of LLM reliability patterns including retries with backoff and jitter, circuit breakers, and fallback models.
• Experience with Docker and cloud-native deployment; ability to own ambiguous, integration-heavy problems and explain technical decisions in depth.

Nice to have

• Direct experience with Amazon Bedrock Agent Core, including agent registration, MCP tool wiring, memory/session management, and gateway provisioning.
• Experience in regulated or high-stakes domains such as education, healthcare, or financial services.
• Familiarity with Step Functions, Sequencer, or similar state-machine workflow orchestration tools.
• Production experience with LLM observability tooling.

Culture & Benefits

• Work on cross-functional teams delivering production-ready AI systems in 30–45 days.
• Collaborate with product, design, and delivery leads across global teams.
• Contribute to technical standards, architecture decisions, and agentic engineering practices.
• Remote work arrangement in Canada.