THE ROLE

We’re seeking a highly skilled and pragmatic AI Engineer with a deep understanding of LLMs, prompt engineering, RAG pipelines, and vector databases to join our growing AI team. This role is critical in designing, developing, and scaling Canyon’s custom AI agents — powering use cases from internal productivity tools to customer-facing digital experiences. 

You’ll play a pivotal role in shaping the future of AI at Canyon by: 

• Building internal and external AI agents 

• Leading prompt engineering and optimization 

• Developing performant and scalable RAG architectures 

• Defining and tracking metrics for AI agent effectiveness 

YOUR JOB AS PART OF THE CANYON CREW

• AI Agent Development: Design, implement, and maintain intelligent agents that interface with users (e.g., customer service, internal tools, e-commerce assistants). 

• Prompt Engineering: Own the development, testing, and iteration of system and user prompts to optimize behavior of GPT-based agents (currently via Azure OpenAI). 

• Content Ingestion / RAG: Implement robust pipelines for retrieval-augmented generation, using Pinecone and other tools to enable dynamic context-aware responses. 

• Performance Analytics: Define and track metrics (latency, accuracy, engagement, satisfaction) for AI agent behavior. Integrate feedback loops to improve performance. 

• Model Tuning & Evaluation: Support fine-tuning and evaluation of LLMs when needed, leveraging our custom data to improve relevance and response quality. 

• Collaboration: Work closely with product managers, designers, and business stakeholders to shape AI use cases and ensure successful deployment. 

• MLOps & Deployment: Help build a robust and maintainable AI infrastructure, including monitoring, versioning, and deployment practices. 

HOW YOU BECOME PART OF THE RACE

• Proven experience in LLM-based development (OpenAI, Azure AI, or open-source models like LLaMA/Mistral). 

• Solid knowledge of prompt engineering techniques, system prompt design, and guardrail implementation. 

• Strong Python skills and familiarity with AI/ML libraries (LangChain, Haystack, Hugging Face, etc.). 

• Experience with vector databases (e.g., Pinecone, Weaviate, FAISS) and RAG pipelines. 

• Understanding of MLOps practices, monitoring tools, and CI/CD for AI workflows. 

• Familiarity with REST APIs, webhook integrations, and cloud services (preferably Azure). 

• Ability to communicate clearly and work across cross-functional teams. 

• Curiosity, pragmatism, and a drive to ship working products fast. 

Nice to Have 

• Experience building AI-powered experiences in e-commerce or DTC environments. 

• Background in machine learning, NLP, or academic training in AI. 

• Understanding of AI ethics, bias mitigation, and data privacy best practices.