Staff AI Search Infra Architect - Cortex

Fdetimes; Menlo Park (CA); On-site; USD 180,000 - 260,000; Full time

Job summary

Snowflake is hiring for a senior AI infra role focused on the Cortex Search infrastructure. You will build high-performance retrieval engines leveraging vector search and semantic indexing to scale billions of rows with millisecond latency.

The role emphasizes multi-tenant microservices, guardrails, and observability. Requires 9+ years in distributed systems and Go/Java with Python for orchestration, in a US-based environment.

Qualifications

• Bachelor’s degree in Computer Science or a related technical field.
• 9+ years of experience building distributed systems, high-throughput APIs, or backend infrastructure for AI/ML products.
• Deep proficiency in Go or Java (for systems) and Python (for AI orchestration).
• Strong understanding of database internals, distributed state management, and cloud-native architecture (Kubernetes, FoundationDB).
• Familiarity with vector indices, agent platforms, and scalable data pipelines.

Responsibilities

• Architect Agentic Runtimes: build and scale orchestration engines for low-latency tool execution and state management.
• Scale Context Engineering Infra: design high-performance systems for RAG, vector databases, indexing, and semantic caching.
• Build the 'Evals Engine': create automation for large-scale simulations and experiments.
• Produce AI Workflows: turn LLM capabilities into hardened, multi-tenant microservices with guardrails.
• Optimize Performance & Cost: guide model routing, prompt caching, and token optimization for efficiency.

Skills

Go or Java

Python

Distributed systems

Backend APIs

Cloud-native architecture

Database internals

Education

Bachelor’s degree in Computer Science or related field

Tools

Kubernetes

FoundationDB

Job description

Snowflake is hiring for a senior AI infra role focused on the Cortex Search infrastructure. You will build high-performance retrieval engines leveraging vector search and semantic indexing to scale billions of rows with millisecond latency.

The role emphasizes multi-tenant microservices, guardrails, and observability. Requires 9+ years in distributed systems and Go/Java with Python for orchestration, in a US-based environment.