Software Engineer, Cortex AI Infrastructure

At Snowflake, we are powering the era of the agentic enterprise. To usher in this new era, we seek AI-native thinkers who are energized by the opportunity to reinvent how they work. The Cortex Apps team is building the future of AI for enterprise data, and this role focuses on the backend infrastructure that powers our flagship products like Snowflake Intelligence, Cortex

Agents, and Search. You won't just be using AI tools; you will be building the high-performance systems that orchestrate them, making agentic AI fast, reliable, scalable, and secure at the enterprise level.

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

- Scale Context Engineering Infra: Develop and design high-performance systems for RAG (Retrieval-Augmented Generation), including vector database integration, scalable search indexing, query processing, and semantic caching.

- Develop the "Evals Engine": Build the automated infrastructure required to run massive-scale golden set simulations, error analysis pipelines, and 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: Implement system optimizations for model routing, prompt caching, and token optimization to ensure maximum efficiency.

- Education: Bachelor's degree in Computer Science or a related technical field; Masters or PhD preferred.

- Experience: 4+ years of industry experience designing, building, and supporting distributed systems, high-throughput APIs, machine learning platforms, or data-intensive systems.

- Technical Stack: Deep proficiency in Python (for AI orchestration) and strong experience with Go or Java (for systems). Familiarity with C++ is a plus.

- Systems Thinking: Strong understanding of database internals, distributed state management, and cloud-native architecture (e.g., Kubernetes, FoundationDB). Experience setting up and maintaining CI/CD pipelines is a plus.

- Domain Expertise: Familiarity with the "plumbing" of AI, such as vector indices, agent platforms, building scalable data pipelines, and working with frameworks like PyTorch, TensorFlow, or XGBoost.

- Mindset: A growth mindset and excitement about breaking the status quo by seeking innovative solutions.

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

- Developing search infrastructure for large-scale applications