Staff Software Development - Full Stack

At Snowflake, we are powering the era of the agentic enterprise. To usher in this new era, we seek AI-native thinkers across every function who are energized by the opportunity to reinvent how they work. You don’t just use tools; you possess an innate curiosity, treating AI as a high-trust collaborator that is core to how you solve problems and accelerate your impact. We look for low-ego individuals who thrive in dynamic and fast-moving environments and move with an experimental mindset — who rapidly test emerging capabilities to discover simpler, more powerful ways to deliver results. At Snowflake, your role isn't just to execute a function, but to help redefine the future of how work gets done.

• Experience designing AI agents with tool/function calling, multi-step planning, and orchestration across multiple agents

• Familiarity with agent frameworks and platforms (e.g., Snowflake Cortex Agents, Model Context Protocol (MCP), LangGraph, or similar)

• Experience with retrieval-augmented generation (RAG), semantic search, and grounding agents on structured and unstructured enterprise data

• Ability to build evaluation sets, measure agent accuracy, and iterate on prompts, tools, and workflows

• Understanding of agent safety and governance: role-based access, auditability, approval gates, and failure handling for actions affecting financial records

• Experience building or extending agent harnesses: the control loop, tool registry and schemas, retries, timeouts, and error recovery

• Context engineering: managing context windows, summarization and compaction, memory, and selecting the right data, instructions, and skills for each step

• Designing tools and MCP servers that are safe, well-scoped, and easy for models to use correctly

• Building permission models, sandboxed execution, and approval checkpoints for agents that read or write sensitive systems

• Building evaluation harnesses and regression suites (golden datasets, LLM-as-judge, trace replay) to measure agent quality before and after changes

• Instrumenting agents with tracing, logging, cost, and latency monitoring to debug behavior in production

• Strong hands-on experience with AI models for code generation (e.g., Anthropic's Claude, OpenAI's GPT-Codex) or similar, for:

• Code generation, refactoring, and debugging

• Designing structured prompts and reusable workflows

• Ability to create and manage skills and profiles in AI models to streamline development tasks

• Experience with AI-assisted development (Claude co-work model) to improve productivity and code quality

• Familiarity with prompt engineering, reasoning workflows, and human-in-the-loop systems