Staff Engineer – AI Builder

Robots & Pencils

. Design and build agentic workflows, including reasoning loops, tool/function calling, and single- and multi-agent architectures .

Posted 10/7/2026full-timeRemote • CanadaLead💰 CA$176,612 - CA$243,680 per yearWebsite

Core Competencies

Role fit

Core Competencies

Use this summary to align your resume positioning with the role.

Demonstrates expertise in building and maintaining GenAI/LLM-powered systems, with a strong focus on agentic AI, RAG pipelines, and AWS technologies. Proficient in prompt engineering, production reliability patterns, and full-stack development.

Highest-signal resume keywords

Agentic AI ExpertiseRAG Pipeline DevelopmentAWS GenAI Stack ProficiencyPython and Node.js DevelopmentProduction Reliability Patterns

ATS Keywords

Tailor your resume

Applicant Tracking System Keywords

Tip: use these terms in your resume and cover letter to boost ATS matches.

Hard Skills

Agentic AIRAG ExpertisePrompt EngineeringFull-Stack DevelopmentProduction Reliability PatternsChunking StrategiesVector DatabasesObservability MetricsRESTful APIsDocker

Soft Skills

MentoringCommunicationProblem-Solving

Tools & Technologies

AWS BedrockOpenSearchLangFuseLangSmithDynamoDBStep FunctionsSQSEventBridgeLambdaDocker

Industry Keywords

GenAILLMMulti-Agent OrchestrationProduction SystemsHigh-Stakes Domain Experience

Tech Stack

Tools & technologies

AWSCloudDockerDynamoDBJavaScriptNode.jsPython

About the role

Key responsibilities & impact

Design and build agentic workflows, including reasoning loops, tool/function calling, and single- and multi-agent architectures
Build and maintain RAG pipelines with chunking, embeddings, OpenSearch vector search, re-ranking, and refresh handling
Integrate AWS Bedrock and Agent Core, including MCP-based tool design
Write and iterate on production system prompts
Build evaluation and observability into agents using golden datasets, RAGAS-style metrics, LLM-as-judge, and LangFuse/LangSmith or equivalent tracing
Design failure-handling patterns such as retries, circuit breakers, fallback models, and user-facing degradation handling
Build Python and Node.js backend services and AWS serverless architectures
Design DynamoDB single-table schemas for conversation state, agent memory, and session history
Support event-driven orchestration with Step Functions, SQS, and EventBridge
Contribute to frontend integration points and write tested full-stack code
Support deployment, monitoring, and production troubleshooting in AWS and Docker environments
Participate in architecture discussions and communicate technical trade-offs
Partner with product, design, and delivery leads across global teams
Mentor engineers on agentic engineering practices and AI-assisted development tools
Own features and releases end-to-end, including debugging, hardening, and production reliability

Requirements

What you’ll need

6+ years of professional software engineering experience, including meaningful time shipping GenAI/LLM-powered systems in production
Hands-on depth in agentic AI: reasoning loops, tool/function calling, and multi-agent orchestration
Practical RAG expertise, including chunking strategies, embeddings, vector databases such as OpenSearch, cosine similarity search, and re-ranking
Experience building evaluation and observability for LLM systems, including golden datasets, LLM-as-judge, RAGAS or comparable metrics, and LangFuse/LangSmith tracing
Strong prompt engineering skills
Hands-on experience with AWS GenAI stack: Bedrock, Agent Core, Lambda, DynamoDB single-table design, S3, SQS, EventBridge, and Step Functions
Strong Python and Node.js skills; experience building full-stack applications and RESTful APIs
Understanding of production reliability patterns for LLM-backed systems, including retries/backoff, circuit breakers, and fallback models
Experience with Docker and cloud-native deployment
Ability to own ambiguous, integration-heavy problems
Helpful extras: Amazon Bedrock Agent Core, regulated or high-stakes domain experience, workflow orchestration tools, and production LLM observability tooling