Generative AI Engineer

Role overview A remote role for an engineer to design and deliver production-grade LLM applications for enterprise clients, from proof of concept through to deployment on major cloud platforms. The work covers retrieval pipelines, agentic workflows, and the governance controls enterprises need to run generative AI safely.

Responsibilities - Design and implement retrieval-augmented generation pipelines, vector search, and document ingestion workflows - Build AI agents and automation workflows integrated with enterprise data platforms - Implement guardrails, access controls, prompt management, and usage monitoring for LLM applications - Collaborate with data engineering teams to connect generative AI solutions to curated lakehouse datasets - Support client workshops, technical discovery sessions, and solution demonstrations

Requirements - 3+ years of software or data engineering experience, including 1+ year focused on LLM or generative AI delivery - Hands-on experience with Azure OpenAI, LangChain, or comparable orchestration frameworks - Working understanding of embedding models, vector databases, and retrieval evaluation techniques - Strong Python skills and familiarity with API-based AI service integration

Nice to have - Experience with Databricks ML, SageMaker, or MLOps tooling - Background in data governance, privacy, or responsible AI practices

Benefits and work setup - Remote position based anywhere in North America - Engagement with enterprise clients across cloud platforms including Azure, AWS, and Databricks