Staff Software Development - Full Stack

Job description

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. Location: Hybrid (3 days) in our Dublin office. We're seeking a Staff Software Engineer – Full Stack in Dublin, California to build and scale the applications and AI agents that power Snowflake's revenue accounting and quote-to-cash processes. You bring 8+ years of full-stack development experience, with deep expertise in AI/ML-powered and agentic systems, including the harnesses that make agents reliable. You've partnered with Revenue Accounting teams, integrated with ERP platforms such as SAP or Oracle, and built AI agents that automate multi-step business workflows. You design scalable applications, integrate LLM capabilities, and raise engineering productivity with tools like Claude Code and Snowflake Cortex AS A STAFF SOFTWARE DEVELOPMENT - FULL STACK FOR THE ET APPLICATIONS TEAM, YOU WILL: - Lead the design and delivery of full-stack applications and agentic systems for Snowflake's finance organization - Architect, build, and deploy AI agents that plan, call tools, and act across finance workflows such as contract review, reconciliation triage, exception resolution, and close-task automation - Own the agent harness (agent loop, tool definitions, context and memory management, permissions, and sandboxed execution) so agents behave predictably on real financial data - Implement guardrails, human-in-the-loop approvals, evaluations, and observability for agents operating on financial data - Partner with Revenue Accounting to automate ASC 606 revenue recognition, including contract processing, revenue schedules, and month-end close - Build and maintain integrations between Snowflake and ERP/revenue systems such as SAP (S/4HANA, RAR) or Oracle (Fusion, Revenue Management Cloud, EBS) - Develop reconciliation, controls, and exception-handling tooling across billing, CRM, and ERP data to keep financial reporting accurate and audit-ready - Drive architecture decisions and set engineering standards for code quality, testing, and AI-native development workflows - Mentor engineers through design and code reviews, and raise the bar on technical excellence - Continuously improve development processes, reliability, and delivery speed OUR IDEAL CANDIDATE WILL HAVE: - Bachelor's or Master's degree in any field - 8+ years of software development experience - Proven experience shipping agentic or LLM-powered applications to production - Hands-on experience with SAP or Oracle financial modules, ideally in revenue accounting or order-to-cash - Working knowledge of revenue recognition (ASC 606 / IFRS 15), contract modifications, and month-end close - Strong SQL and database fundamentals - Experience with modern software development practices - Strong problem-solving and analytical skills - Excellent communication skills and comfort partnering directly with Accounting and Finance. AI-NATIVE ENGINEERING EXPERTISE: - 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 HARNESS ENGINEERING EXPERTISE: - 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 - Instrumen