Data Scientist II

Tavern Research•Chicago, IL

33d•Onsite

About The Position

Dynamic systems are hard to model. Dynamic systems involving human behavior, especially when interactions aren’t directly observable, are even harder. But the stakes are too high not to try. At Tavern Research, we’re building models to understand and influence how people form opinions online. As a Modeler II, you’ll take on substantive projects end-to-end, defining the problem, shaping the data, and designing models that bring clarity to messy, high-impact questions. Your work may include tracking the spread of narratives, modeling how media exposure shapes political attitudes, or developing custom embedding models to follow evolving discourse. Some days you’ll be designing experiments; other days you’ll be debugging noisy datasets or parsing engagement metrics to figure out what’s actually working and why. We believe people’s beliefs are shaped by the information they consume, and that information is increasingly engineered. The internet cracked the door open for opinion manipulation, and language models kicked it wide open. If we care about the future of democracy, we need to understand how influence spreads, mutates, and lands, and help our partners respond with precision and speed. You won’t be handed a clean dataset or a fully formed research question. Instead, you’ll be expected to bring both scientific rigor and creativity to ambiguous, open-ended problems. You’ll collaborate closely with a tight-knit, interdisciplinary team, testing ideas fast, shipping iteratively, and pushing toward real-world impact. While your primary focus will be hands-on modeling, you’ll also support and mentor junior modelers, helping to expand Tavern’s technical depth and build a sustainable senior–junior structure. This is a role for someone who thrives at the edge of research and application, where the data is messy, the problems are wide open, and the answers matter. We value in-person work and expect employees to work regularly from our Chicago office.

Requirements

This role is designed for experienced modelers with 4+ years of experience or demonstrated ability to independently deliver production modeling projects.
Proven track record of leading substantive modeling projects that delivered real-world impact.
Advanced proficiency in Python and modern ML/AI libraries, with ability to write production-quality code.
Extensive experience working with messy, large-scale datasets.
Depth in advanced techniques such as causal inference, topic modeling, network analysis, embeddings, optimization, or agentic systems, with strong grounding in experiment design and statistical evaluation.
Demonstrated ability to evaluate models rigorously and iterate quickly.
Strong communication skills with ability to explain complex concepts clearly to technical and non-technical audiences.
Collaborative mindset and comfort with modern engineering workflows (version control, testing, code review).
Prior experience mentoring or supporting junior modelers, and exposure to production ML pipelines.
To be explicit: you don’t need a degree to work here. You just need to be good at the things we’re asking from you.

Responsibilities

Independently lead the design and analysis of experiments using methods like randomized trials, difference-in-differences, and causal inference.
Build, maintain, and evaluate advanced statistical and machine learning models that generate political and behavioral insights.
Engineer features and build scalable pipelines from messy, real-world datasets.
Write clean, production-ready Python code and documentation.
Drive rigorous model evaluation, diagnostics, and iteration to ensure reliability.
Collaborate with researchers and engineers to translate open-ended questions into solvable modeling approaches.
Contribute to the team’s technical direction by introducing new methods, tools, or frameworks.
Provide peer support and mentorship to junior modelers, helping to grow team capacity.