Product Analyst

Job Description

IntegriChain's Product Management team is adding a Product Analyst for Prism. Prism is our conversational analytics platform. It lets the people who work in market access at life sciences companies ask questions about their data in plain English and get answers back in seconds, instead of handing the request to an analyst and waiting. Behind the scenes, Prism runs on semantic layers we build from our raw SQL data, and those layers are what let it take a business question and map it to the right numbers. The Product Analyst is the person who makes sure the questions people ask actually line up with the answers Prism gives back. You'll work day to day with Product Management, Data Science, and Engineering to keep those answers accurate and worth trusting.

This isn't a development role, and it isn't about building reports or dashboards. It's an analysis role for someone who is technical but isn't a software engineer. You'll use Snowflake Cortex along with tools like Claude and Codex to review and improve the prompts business users type into Prism and the answers it sends back. A lot of the work is finding the spots where the data is set up in a way that leads Prism to misread a question or return the wrong answer. Roughly half the job is digging into the data itself. The other half is talking to the business owners, certifying that queries return the right results, and writing up what needs to change.

What This Role Entails

• Prompt review: Go through the prompts business users type into Prism and improve them, using Snowflake Cortex and tools like Claude and Codex, so their questions get read correctly against the semantic layer.
• Query certification: Check user queries and the answers Prism gives back, confirm they hold up against the source data, and sign off so the business can trust the results.
• Quality ownership: Keep an eye on the questions users ask and the answers they get, and watch for repeat errors, gaps, or misreads so they get fixed.
• Semantic layer work: Work with Data Science and Engineering to improve the semantic layers built from the raw SQL tables, including the taxonomies, metadata, and labeling, so Prism understands the data better.
• Data analysis: Dig into how data connects across pricing, rebates, chargebacks, and other areas, and use what you find to shape how that data is represented in Prism.
• Working with the business: Talk to business owners about the questions they need answered, and turn those conversations into better prompts, queries, and data structure.
• Writing requirements: Write clear technical requirements for tuning the model, changing how data is structured, or improving the product, based on what your reviews turn up.
• Documentation: Document where the data comes from, the business logic behind it, and how things relate, so people can understand and trust Prism's answers.
• Roadmap input: Be the voice for data quality in planning and prioritization for Prism, so decisions are based on what the data actually says.
• QA and communication: Work with QA to set up test cases for answer accuracy each sprint, and help with internal and customer updates (release notes, briefings, presentations) that explain how Prism works.