Senior / Staff Analyst, Tax

What you'll work on

AI Agent and Workflow Development (Primary Focus)

• Partner directly with Tax leadership to re-engineer core tax processes—including compliance, risk identification, and global reporting—into automated, 'AI-first' workflows.
• Design and deploy agentic tools using CoCo and CoWork that reduce manual data gathering, allowing the team to shift focus from data preparation to strategic decision-making and exception handling.
• Write and iterate on prompt & skill structures (YAML + Markdown skill files) based on output quality and stakeholder feedback.

Tax Intelligence & Unification

• Build a unified data and knowledge layer that serves as a single source of truth for all tax-relevant information.
• Transform fragmented data sources into clean, reconciled datasets, and create an 'AI tax brain' that encodes tax laws, internal playbooks, and regulatory updates to enable instant, accurate analysis across domestic and international tax workflows.
• Support risk assessment models and compliance reporting pipelines.

Semantic Layer & Application Development

• Own semantic layers end-to-end — model design, versioning strategy, verified query coverage, and accuracy iteration based on eval metrics.
• Develop and deploy production tax 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.

Tax Reporting and Compliance Automation

• Participate in tax filing cycles — automating tax filings, data reconciliation, and audit-ready reporting.
• Build and maintain source-of-truth reporting exports (multi-tab Excel, formatted to spec).
• Support ad-hoc disclosure and tax audit data needs.

Hard Skills Required

Must-have

• AI-assisted development: Used an LLM coding assistant (CoCo, Cursor, GitHub Copilot, Claude, or equivalent) as primary development tool with a measurable, trackable record of daily AI usage.
• Prompt engineering and skill authoring: Write structured prompts (YAML + Markdown) that route correctly 95% of the time, handle edge cases, and encode domain knowledge.
• Python: Modern, type-hinted, readable code for applications, data pipelines, and reporting automation. At senior level: contributed to shared libraries and designed agent orchestration systems.
• SQL: CTEs, window functions, incremental pipeline patterns.
• Data modeling fundamentals: Bronze/silver/gold models, versioning, evaluation of SQL generation accuracy, verified query libraries.

Strong Plus

• Snowflake Cortex (Cortex Analyst, Cortex Agents, AI_SUMMARIZE, AI_EXTRACT, Dynamic Tables, semantic views)
• SnowWork / CoCo: Deploying agents, authoring skill files
• Finance literacy: Reading revenue waterfalls, distinguishing ARR/NRR
• Reporting automation (openpyxl, multi-tab Excel)
• dbt: Model authoring, ref() patterns, YAML tests
• Semantic search / embeddings: Vector similarity, embedding-based retrieval

Soft Skills Required

• Translates between AI, data, and tax domains for non-technical stakeholders.
• Sets the standard for agent building; mentors juniors and improves shared infrastructure.
• Thinks in reusable workflows and agents rather than one-off tasks.
• Works fast with high accuracy on weekly finance cadences.
• Comfortable with ambiguity.