Snowflake Cortex / LangGraph - Contractor
CloudHive is seeking a highly skilled Snowflake Cortex / LangGraph contractor to help organizations unlock the full potential of Large Language Models (LLMs) within the Snowflake ecosystem. In this role, you’ll design and implement intelligent applications that integrate Snowflake Cortex LLM Functions with LangGraph, enabling advanced AI‑powered query systems, secure data workflows, and real‑time insights.This is a hands‑on engineering role that combines LLM integration expertise, Snowflake architecture knowledge, and modern AI application design.Key ResponsibilitiesBuild and optimize custom LLM integrations between Snowflake Cortex and LangGraph.Develop and extend Python classes to support REST API interactions, token streaming, and guardrail enforcement.Architect multi‑actor, stateful AI applications leveraging LangGraph cycles and agent frameworks.Collaborate with data teams to ensure secure, governed use of Snowflake Cortex LLMs, leveraging RBAC and Snowflake’s native AI capabilities.Design retrieval‑augmented generation (RAG) pipelines and other AI‑driven workflows that connect enterprise data in Snowflake with Cortex LLMs.Optimize for performance, scalability, and cost‑efficiency.Stay current with emerging LLM frameworks, models (Claude, Llama, Mistral, Arctic, Gemma), and Snowflake’s expanding Cortex AI features.Required Skills & ExperienceProven experience with Snowflake, including SQL functions, governance, and data integration.Strong Python development skills, ideally with LangChain / LangGraph experience.Hands‑on expertise integrating REST APIs.Familiarity with enterprise AI architectures (secure model usage, RAG patterns, multi‑actor orchestration).Experience deploying applications that leverage LLMs at scale in production environments.Knowledge of role‑based access controls (RBAC), secure data sharing, and enterprise security considerations.Preferred QualificationsPrior work with Snowflake Cortex LLM FunctionsExperience building intelligent query or analytics systems powered by LLMs.Understanding of AI model tuning, prompt engineering, and guardrails in enterprise contexts.Background in financial services or other regulated industries (a plus but not a necessity).