Staff AI Builder

This is a fully remote position, open to applicants in Canada.

📋 Description

• Oversee the design and implementation of AI/ML systems.

• Establish AI architecture and spearhead model development and optimization.

• Create and implement agentic workflows, which include reasoning loops, tool/function invocation, and orchestration for both single- and multi-agent systems.

• Develop and sustain RAG pipelines featuring chunking, embeddings, OpenSearch vector search, re-ranking, and refresh handling.

• Integrate AWS Bedrock and Agent Core, with an emphasis on MCP-based tool design.

• Compose and refine production system prompts.

• Incorporate evaluation and observability into agents utilizing golden datasets, RAGAS-style metrics, LLM-as-judge, and tracing.

• Design for potential LLM failures through retries, backoff mechanisms, circuit breakers, fallback models, and user-facing degradation handling.

• Construct backend services using Python and Node.js, including serverless architectures with AWS Lambda and API Gateway.

• Create DynamoDB single-table schemas for managing conversation state, agent memory, and session history.

• Facilitate event-driven orchestration utilizing Step Functions, SQS, and EventBridge.

• Contribute to frontend integration points and produce clean, tested code across the technology stack.

• Assist in deployment, monitoring, and troubleshooting in AWS and Docker environments.

• Collaborate with product, design, and delivery leaders across global teams to scope and deliver features end-to-end.

• Mentor engineers and enhance agentic engineering practices, including the use of Claude Code.

• Take ownership of features and releases throughout the entire process, including debugging, hardening, and ensuring production reliability.

⛳️ Requirements

• A minimum of 6 years of professional software engineering experience, including significant time spent deploying GenAI/LLM-powered systems in production.

• In-depth hands-on experience in agentic AI, including reasoning loops, tool/function invocation, and multi-agent orchestration.

• Practical expertise in RAG, encompassing chunking strategies, embeddings, vector databases like OpenSearch or equivalent, cosine similarity search, and re-ranking.

• Proven experience in building evaluation and observability frameworks for LLM systems, including golden datasets, LLM-as-judge, RAGAS or similar metrics, and tracing tools like LangFuse/LangSmith.

• Strong skills in prompt engineering.

• Hands-on experience with the AWS GenAI stack: Bedrock, Agent Core, Lambda, DynamoDB single-table design, S3, SQS, EventBridge, and Step Functions.

• Proficiency in Python and Node.js.

• Experience in developing full-stack applications and RESTful APIs.

• Understanding of production reliability patterns relevant to LLM-backed systems, including retries/backoff, circuit breakers, and fallback models.

• Familiarity with Docker and cloud-native deployment.

• Capability to tackle ambiguous, integration-heavy challenges and provide technically sound solutions.

• Additional assets: direct experience with Bedrock Agent Core; background in regulated or high-stakes domains; knowledge of workflow orchestration; experience with production LLM observability.

🏝️ Benefits

• Competitive salary and performance-based bonuses.

• Flexible working hours and remote working opportunities.

• Comprehensive health, dental, and vision insurance.

• Opportunities for professional development and continuous learning.

• Collaborative and inclusive work environment.