SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Commenda helps multinational companies navigate indirect tax, entity management, transfer pricing, and corporate tax across 50+ jurisdictions. The company's core mission is to schematize and index every law relevant to its customers—a challenge because tax law is fractally complex, with 14,000 US taxing jurisdictions alone, each with tiered rates, partial exemptions, and product-category-based rules.
You will own the schemas, automated research systems, and evaluation infrastructure that keep Commenda's structured knowledge base current and correct. Your work powers the tax engine, filings, dashboards, AI products, and Commenda Media (the company's public research arm).
Key responsibilities:
- Schematize laws by reading statutes, regulations, and administrative guidance from primary sources; design schemas that capture what they actually say; decide when new jurisdictions require model changes.
- Automate research by building hosted, agentic research workflows: LLM pipelines that research jurisdictions, populate schemas, and cross-check their own work (researcher/evaluator agent pairs, not one-shot prompts).
- Own the infrastructure these pipelines run on.
- Evaluate and measure output relentlessly: build eval suites, adversarial test cases, and fuzzing harnesses to verify correctness.
- Design ground-truth datasets and measure the difference between 99% accurate and actually correct.
- Drive down the marginal cost of adding jurisdiction N+1 from weeks of human research toward hours of human review.
- Ensure freshness: measure and optimize the time from when a law changes to when it's reflected in the index.
- Guarantee correctness: no customer outcome should ever be wrong because the index was wrong, stale, or difficult to understand.
You'll be part of a three-person team alongside the CTO and a research economist, with outsized impact across all product teams.
Requirements:
- Extreme sense of ownership and urgency; consciousness that your output directly affects customer compliance outcomes, lost money, time, and trust.
- Software engineering background with ability to build and operate real systems (data pipelines, APIs, evaluation infrastructure).
- Strong schema design skills: instincts for modeling messy real-world domains in structured form; taste for generalization vs. special-casing; ability to defend data model decisions.
- Preferred (not required): experience using AI to automate knowledge work; background in tax, law, finance, or another detail-dense regulated domain.
