Senior Software Engineer - Cortex AI - FDE

What you will do in this role:

• Architect Agentic Runtimes: Build and scale the orchestration engines that execute complex agentic workflows, ensuring low-latency tool execution and robust state management.

• Scale Context Engineering Infra: Design high-performance systems for RAG (Retrieval-Augmented Generation), including vector database integration, scalable and efficient search indexing, query processing, and result ranking, semantic caching, and automated metadata extraction.

• Build the "Evals Engine": Develop the automated infrastructure required to run massive-scale golden set simulations, error analysis pipelines, and "hillclimbing" experiments.

• Productionize AI Workflows: Collaborate with the modeling team to take raw LLM capabilities and turn them into hardened, multi-tenant microservices with strict guardrails and observability.

• Optimize Performance & Cost: Direct the infra strategy for model routing, prompt caching, and token optimization to ensure Snowflake’s AI features are the most efficient in the industry.

Requirements:

• Education: Bachelor’s degree in Computer Science or a related technical field.

• Experience: 7+ years of experience building distributed systems, high-throughput APIs, or backend infrastructure for AI/ML products.

• Technical Stack: Deep proficiency in Go or Java (for systems) and Python (for AI orchestration).

• Systems Thinking: Strong understanding of database internals, distributed state management, and cloud-native architecture (Kubernetes, FoundationDB, etc.).

• Domain Expertise: Familiarity with the "plumbing" of AI: vector indices, agent platforms, and building scalable data pipelines.

• Experience in a customer-facing technical role — you have explained a hard failure to a frustrated external audience and been believed, you can produce both the internal analysis and the customer-safe version.

• Product instinct — you can judge whether one customer's problem is bespoke or a platform gap worth fixing for everyone. This is the core judgment call.

• Cross-layer debugging — tracing a request across services and root-causing in unfamiliar code from logs and telemetry, not guesswork.

• Eval frameworks for LLM/agent systems — defining quality metrics and using evals to improve quality systematically over time.

• Comfort with ambiguity on open-ended, externally-driven problems.

(Bonus) Experience with:

• Query optimization and SQL engine internals.

• Designing multi-tenant systems that handle sensitive enterprise data at scale.

• Developing search infrastructure for large-scale applications.

• Direct experience with any of the subsystems outlined above.