Snowflake Cortex & LLMs - GEN AI - Lead / Architect

Role Overview

We are seeking a Cloud-Native AI Architect to build scalable, microservice-driven AI platforms combining Snowflake Cortex AI with modern cloud infrastructure. You will architect event-driven agent systems, serverless execution pipelines, and secure API integrations to bridge Snowflakes in-database AI with cloud-native applications.

Key Responsibilities

• Architect Cloud AI Ecosystems: Design microservice-based, event-driven agent pipelines using Kubernetes, serverless tools, API gateways, and cloud messaging (Kafka/EventBridge).
• Snowflake Cortex Integration: Direct the integration of Snowflake Cortex AI (Cortex Agents, Search, Analyst, Native Functions) via Snowpark Python and enterprise APIs.
• Agent Framework Strategy: Standardize containerized agent orchestration (LangGraph, AutoGen, CrewAI, LlamaIndex) for production cloud deployments.
• Cloud Security & Identity: Implement zero-trust boundaries, OAuth2/OIDC, Non-Human Identity (NHI) controls, and prompt injection guardrails across cloud and data platforms.
• LLMOps & IaC: Define Infrastructure-as-Code (Terraform), CI/CD pipelines, and OpenTelemetry-based tracing for LLM performance, latency, and costs.

Core Requirements

• Cloud Infrastructure: Deep mastery of AWS, Azure, or GCP (EKS/AKS, Lambda/Functions, Terraform, Docker).
• Tech Stack: Expert Python (FastAPI, PyDantic) and Snowflake SQL / Snowpark.
• AI & Cortex: Architect-level experience with Snowflake Cortex, RAG architectures, dynamic tool-calling, and autonomous agent loops.