Senior AI Infra Engineer - Agentic Systems

RiseMe; Menlo Park (CA); On-site; USD 180,000 - 240,000; Full time

Job summary

Snowflake is building the Cortex Apps backend to power enterprise AI. You will design and optimize agent execution environments and high-throughput context retrieval in production.

Collaborate with modeling teams to turn LLM capabilities into hardened multi-tenant microservices with guardrails and observability. You will prioritize performance, cost, and reliability to keep Snowflake at the forefront of AI for data.

Qualifications

• Bachelor’s degree in Computer Science or related technical field.
• 7+ years building distributed systems or AI/ML backend infra.
• Proficiency in Go/Java and Python for orchestration.
• Strong cloud-native architecture and Kubernetes expertise.
• Familiarity with vector indices and scalable data pipelines.

Responsibilities

• Architect agent runtimes and low-latency tool orchestration.
• Scale context engineering infra for RAG and vector DB integration.
• Develop the Evals Engine for large-scale simulations.
• Productionize AI workflows into multi-tenant microservices.
• Optimize model routing, caching, and cost across infra.

Skills

Go/Java

Python

Distributed systems

Kubernetes

Cross-layer debugging

LLM evals

Customer-facing

Education

Bachelor's degree in Computer Science or related field

Tools

FoundationDB

Vector DB

Job description

Snowflake is building the Cortex Apps backend to power enterprise AI. You will design and optimize agent execution environments and high-throughput context retrieval in production.

Collaborate with modeling teams to turn LLM capabilities into hardened multi-tenant microservices with guardrails and observability. You will prioritize performance, cost, and reliability to keep Snowflake at the forefront of AI for data.