SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Snowflake is seeking a Staff Software Engineer – Full Stack to build and scale AI-native applications and agentic systems powering the company's revenue accounting and quote-to-cash processes. This is a hybrid role (3 days on-site) in the Dublin, California office.
You will lead the design and delivery of full-stack applications and agentic systems for Snowflake's finance organization. Key responsibilities include:
- Architect, build, and deploy AI agents that automate multi-step 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, sandboxed execution) ensuring agents behave predictably on real financial data
- Implement guardrails, human-in-the-loop approvals, evaluations, and observability for agents operating on sensitive 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
- Drive architecture decisions and set engineering standards for code quality, testing, and AI-native development workflows
- Mentor engineers through design and code reviews, raising the bar on technical excellence
- Continuously improve development processes, reliability, and delivery speed
Snowflake emphasizes an AI-native culture where you treat AI as a high-trust collaborator core to problem-solving. The role sits at the intersection of engineering, finance, and agentic AI, with direct impact on how Snowflake recognizes and reports revenue.
REQUIREMENTS:
- 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
- Instrumenting agents with tracing, logging, cost, and latency monitoring to debug behavior in production
PREFERRED:
- Strong hands-on experience with AI models for code generation (e.g., Anthropic's Claude, OpenAI's GPT-Codex) for code generation, refactoring, and debugging
- 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
