Data Scientist, Product
About The Position
Ascend is transforming the insurance industry, a $10T sector currently reliant on outdated systems like PDFs and manual processes. We provide the first and only comprehensive financial operations platform designed specifically for insurance, integrating AI-powered accounting automation, payments, and premium financing. Our solution brings clarity to complex accounting operations, from collection to close. Ascend automates daily financial operations for insurers, MGAs, and agencies, embedding directly into transactions. We believe AI will drive software costs down and that companies capturing value at the point of transaction will win. Our customers achieve significant efficiency gains with a proven 5-7x return on investment. Our approximately 100-person team, based in San Francisco and Columbus, possesses deep expertise in insurance, fintech, and AI, focused on building essential industry infrastructure. Our mission is to become the leading financial automation platform for insurance by 2030, powering the industry's financial operations and modernizing how trillions of dollars move. We are building the financial backbone of the insurance industry, not just another point solution.
Requirements
- Owned product data inside a live workflow rather than reporting on one.
- Deployed a model into a live workflow and owned it afterward, including calibration, drift, and the call to re-fit or retire.
- Comfortable explaining calibration, drift, predicted-versus-realized, and re-fit timing to a non-technical owner.
- Strong in SQL and feature engineering.
- Thrives in the ambiguity of an early-stage startup.
- Will say when the data is too weak to decide, then propose a next step anyway.
- Experience working in Slack, Notion, Excel, Front, and Linear.
- Strong written and verbal communication skills.
- Ability to quickly understand complex (and sometimes dense) subject matter.
- Great attention to detail.
Nice To Haves
- Experience with payments is a plus.
Responsibilities
- Settle metric definitions that three teams currently disagree on.
- Set thresholds that decide when a human touches a document.
- Stay accountable for thresholds after they go live.
- Get deep into Ascend's products, data infrastructure, and metric definitions.
- Build relationships with Product, Engineering, and the Head of Data to understand measurement decision-making.
- Audit production scores and thresholds and map missing instrumentation.
- Propose and settle accuracy, success, and exception metrics for Ascend's products.
- Own thresholds that determine system actions versus human routing.
- Partner with Product and Engineering on instrumentation for upcoming features.
- Fully own accuracy, success, and exception metrics across all products.
- Build and ship models that change workflows, not just describe them (e.g., confidence scoring, ranking/matching for reconciliation, sequencing for collections).
- Monitor all production scores (predicted vs. realized, drift) and set re-fit or retire dates.
- Design experiments that the volume can support.
- Turn product usage data into roadmap input.
Stand Out From the Crowd
Upload your resume and get instant feedback on how well it matches this job.
What This Job Offers
Job Type
Full-time
Career Level
Senior
Education Level
No Education Listed
