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 guide the development and optimization of models.

• Address complex integration challenges with a focus on reliability, security, and scalability.

• Create and develop agentic workflows, encompassing reasoning loops, tool/function invocation, and orchestration for both single and multi-agent setups.

• Construct and manage RAG pipelines that include chunking, embeddings, vector search, re-ranking, and handling of knowledge refresh.

• Integrate AWS Bedrock with Agent Core, featuring tool design based on MCP.

• Compose and refine prompts for production systems.

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

• Develop strategies for failure management, including retries, circuit breakers, fallback models, and user-facing degradation paths.

• Create backend services using Python and Node.js, alongside AWS serverless architectures.

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

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

• Participate in frontend integration and produce thoroughly tested full-stack code.

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

• Collaborate with product, design, and delivery teams globally to define and implement features.

• Mentor engineers on agentic engineering methodologies and AI-assisted development tools.

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

⛳️ Requirements

• Minimum of 6 years of professional software engineering experience, with significant involvement in deploying GenAI/LLM-powered systems in production.

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

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

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

• Strong skills in prompt engineering.

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

• Proficient in Python and Node.js, with a background in developing full-stack applications and RESTful APIs.

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

• Experience with Docker and cloud-native deployment practices.

• Ability to thrive in ambiguous, integration-heavy situations and delve deeper into technical solutions.

• Additional assets include experience with Amazon Bedrock Agent Core, working in regulated or high-stakes domains, familiarity with workflow orchestration tools, and production-level LLM observability tools.

🏝️ Benefits

• Competitive salary and performance bonuses.

• Flexible working hours and remote work opportunities.

• Comprehensive health and wellness benefits.

• Opportunities for professional development and training.

• A collaborative and innovative work environment.