> Markdown version of [/jobs/ext/4689987-data-scientist-lead-generation](https://www.wearedevelopers.com/jobs/ext/4689987-data-scientist-lead-generation). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md). --- # Data Scientist, Lead Generation - **Company:** Washington and Idaho Railway Inc - **Location:** United States (Remote available) - **Experience:** Expert - **Salary:** $175,000 - $200,000 - **Contract:** Permanent contract - **Skills:** Training Data, Amazon S3, Artificial Neural Networks, Continuous Integration, High-Level Architecture, Python (Programming Language), Recommender Systems, Standard Sql, Delivery Pipeline, Loss Functions, Performance Monitor, AWS Data Analytics, Machine Learning Operations - **Published:** November 12, 2026 - **Apply:** https://arc.dev/remote-jobs/j/redirect/pyvt91x8x1 ## About the Role * Minimum of 5 years of applied data science experience with demonstrable business impact * Proven track record of building models that drive paid media decisions such as spend allocation, bidding strategies, or ad serving (attribution and reporting experience alone is insufficient) * Deep understanding of model architectures, loss functions, and neural network fundamentals, with the ability to clearly explain your work * Experience managing challenges such as late labels, sparse features, data drift, and understanding how bidding influences future training data * End-to-end ownership of models including data sourcing, development, deployment, and ongoing monitoring * Expert proficiency in Python and SQL * Preferred but not required: experience with large-scale ranking or recommendation systems, live ad budget auctions, neural network applications (e.g., embeddings of text or user behavior), AWS data science tools (ECS, S3, Athena, SageMaker), CI/CD deployment pipelines, and communicating technical tradeoffs to non-technical stakeholders ## Description We are seeking a highly skilled Data Scientist to own and develop predictive models that determine which auto insurance carrier each shopper sees on our click wall. The primary objective is to optimize user-to-carrier matching to maximize conversion rates, thereby encouraging carriers to increase their bids. You will also be responsible for building and maintaining buying models that govern our media spend, measured by Return on Ad Spend (ROAS). This role requires hands-on involvement in framing problems, sourcing data, building and validating models, and overseeing deployment and monitoring. You will collaborate closely with an ML engineer who supports production infrastructure. Initially, your focus will be on the auto insurance vertical, with opportunities to expand into other sectors over time. The position is remote-first, with most team members working East Coast hours., * Develop and maintain predictive models that optimize user-carrier matching on the auto insurance click wall * Build and refine media buying models to maximize ROAS and optimize bidding strategies * Collaborate with business stakeholders to frame problems and translate requirements into modeling solutions * Source, clean, and analyze complex and sparse data sets with delayed outcome feedback * Deploy models into production and monitor performance, addressing data drift and changing business objectives * Work alongside ML engineers to ensure robust model integration and scalability * Expand modeling efforts beyond auto insurance to other verticals as the role evolves * Communicate insights and model implications effectively to both technical and non-technical partners