SlipstreamJobsFresh Startup & VC-Backed Jobs

Senior Software Engineer - Cortex AI - FDE

Snowflake - Menlo Park, CA, United States - In-office - posted 2026-08-11

Apply on the company site

SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.

Snowflake's Cortex Apps team is building enterprise-grade AI infrastructure to power agentic workflows at scale. This Senior Software Engineer role focuses on backend systems that orchestrate complex AI agents, manage high-throughput context retrieval, and enable production-ready AI features for enterprise customers. You will architect and own critical infrastructure components including agentic runtime orchestration engines, high-performance RAG (Retrieval-Augmented Generation) systems with vector database integration, and evaluation frameworks for LLM/agent quality assurance. Your work will directly impact how Snowflake's Intelligence, Cortex Agents, and Search products perform at enterprise scale. Key responsibilities include designing low-latency agent execution environments with robust state management, building scalable search indexing and query processing pipelines, developing automated evaluation infrastructure for golden-set simulations and error analysis, and collaborating with modeling teams to productionize raw LLM capabilities into hardened multi-tenant microservices. You'll optimize performance and cost through model routing, prompt caching, and token optimization strategies. The ideal candidate brings 7+ years of distributed systems and backend infrastructure experience, with deep proficiency in Go or Java for systems work and Python for AI orchestration. You should have strong systems thinking around database internals, distributed state management, and cloud-native architecture (Kubernetes, FoundationDB). Domain expertise in vector indices, agent platforms, and data pipelines is essential. Experience explaining technical failures to customers, making product judgment calls about platform gaps, cross-layer debugging across services, and defining quality metrics for LLM systems is highly valued. Bonus experience includes query optimization, SQL engine internals, multi-tenant system design for sensitive data, and search infrastructure development.

Similar roles