Senior/ Staff Analyst, Finance Analytics & AI

About the role

We are an AI-first analytics team. Our primary development environment is CoCo and SnowWork, the AI IDE we ship work in. Every deliverable on this team is built AI-first: you design the workflow, you write the prompt, you validate the output.

Responsibilities

• AI agent and workflow development (primary focus)
• Design and build skills and agentic experiences that encode repeatable finance workflows into reusable, invokable tools using CoCo and CoWorkWrite and iterate on prompt & skill structures based on output quality and stakeholder feedback
• Evaluate model outputs rigorously — you are the quality gate before anything reaches a finance stakeholder
• Build and maintain quarterly and weekly revenue summary pipelines
• Support sensitivity analysis models for quarterly business reviews & revenue forecast scenarios
• Produce ad-hoc analysis for Strategic Finance
• Own semantic layers end-to-end — model design, versioning strategy, verified query coverage, and accuracy iteration based on eval metrics; not just build models, but maintain the contract between the model and its consumers across each quarterly iteration
• Develop and deploy production finance dashboards as Streamlit apps (locally and deployed to Snowflake)
• Build customer-facing demo applications for Sales and Field teams
• Apply reusable component patterns and shared utility libraries for consistent, polished UI
• Participate in quarterly earnings cycle prep — scenario tooling, export automation, IR data requests
• Build and maintain source-of-truth reporting exports (multi-tab Excel, formatted to spec)
• Support ad-hoc disclosure and investor relations data needs during quarter-end

Requirements

• Must-have AI-assisted development — You have used an LLM coding assistant (CoCo, Cursor, GitHub Copilot, Claude, or equivalent) as your primary development tool. You know how to write a prompt that produces production-ready output, how to steer a model that's heading in the wrong direction, and how to encode domain logic into a reusable, parameterized skill. You have a measurable, trackable record of daily AI usage.
• Prompt engineering and skill authoring — You can write a structured prompt (YAML + Markdown or equivalent) that routes correctly 95% of the time, handles edge cases gracefully, and encodes enough domain knowledge that the model behaves like a subject matter expert. You think in terms of context, instructions, examples, and output format — not just "the thing I typed before the code came out."
• Python — Modern, type-hinted, readable. You write Python-based applications, data pipelines, and reporting automation. You understand caching, session state, and how to structure a multi-page app cleanly.
• SQL — CTEs, window functions, incremental pipeline patterns. You don't look up the syntax for a row-numbered deduplication.
• Data modeling fundamentals — You understand bronze, silver, and gold data models conceptually and contribute to the gold layers and how they translate to semantic layer. You know not just how to build a model, but how to version it, evaluate SQL generation accuracy, maintain a verified query library, and iterate based on real analyst feedback. A non-technical user should be able to query your model in plain English and get a correct answer.
• Strong plus Snowflake Cortex — Cortex Analyst, Cortex Agents, AI_SUMMARIZE, AI_EXTRACT, Dynamic Tables, semantic viewsSnowWork / CoCo — Prior experience deploying agents, authoring skill files, or working within the Snowflake Intelligence ecosystem
• Finance literacy — You can read a revenue waterfall, distinguish ARR from NRR, and explain what drives a QoQ change in product revenue
• Reporting automation — openpyxl, multi-tab Excel exports formatted to spec, named rangesdbt — Model authoring, ref() patterns, YAML tests in a cloud warehouse context
• Semantic search / embeddings — Vector similarity, embedding-based retrieval, and how they power natural language analytics

Qualifications

• 3-5+ years of experience in analytics, data engineering, or a technical finance adjacent role
• Has used an AI coding assistant as a primary development tool — daily usage, not occasional
• Proficient in SQL — you can write a window function without looking it up
• Shipped multiple Python applications that end-users actually interacted with; at least one is actively maintained in production
• Comfortable working in Git (PRs, branches, code review)
• Familiar with fiscal year concepts and core revenue metrics (ARR, bookings, NRR)