AI Engineer

About the role

We are looking for a hands-on AI / ML Engineer to turn technical vision into robust, live, and monitored AI products. Working alongside our Senior Data Scientist, you will own the end-to-end engineering behind our LLM applications, RAG pipelines, and AI agents built on top of a modern enterprise cloud data platform.

Key responsibilities

• Build and deploy production-grade LLM applications, RAG systems, and multi-agent workflows from data science designs
• Prepare, optimize, and connect data pipelines to feed AI/LLM applications using strong Python and SQL engineering
• Own CI/CD, testing, continuous monitoring, performance tuning, and incident management for live AI services
• Ensure high availability, low latency, and continuous evaluation for operational AI systems

About you

• 3–5 years of hands-on experience across AI, ML, Data, or Software Engineering
• Advanced Python and SQL proficiency
• Solid expertise working with modern cloud data platforms (data prep, performance tuning, and integration)
• Proven experience building and deploying GenAI products (RAG pipelines, AI agents, prompt management, and evaluation frameworks)
• Hands-on knowledge of CI/CD, unit/integration testing, observability, and troubleshooting live production systems
• Exposure to platform-native AI search, agent tools, or developer frameworks (e.g., Snowflake Cortex / Snowpark) – nice-to-have
• Experience with LLM observability, tracing, and evaluation tools – nice-to-have
• Background in traditional ML pipelines (deployment, drift monitoring, retraining) – nice-to-have
• Exposure to the Microsoft AI stack (Azure AI, Power Platform, Copilot) – nice-to-have