Applied Scientist, Behavior Modeling

Shuttlebase; New York (NY); On-site; USD 140,000 - 195,000; Full time

Benefits offered by this job

Competitive compensation

Equity grants

Medical, dental, vision coverage

Unlimited PTO

Office in Midtown Manhattan

Job summary

Shuttlebase is building a pioneering behavior model to quantify how users interact with online stores. You will design and implement embeddings from event sequences, pre-train transformers, and decide on data representations that capture real purchase intent.

You’ll work closely with engineers, researchers, and the CTO to translate findings into live experiments. Based in Midtown Manhattan, Shuttlebase offers meaningful equity, comprehensive benefits, and a collaborative, research-driven

Qualifications

• PhD or equivalent research experience in a quantitative field.
• Experience training models on messy, real-world sequence or time-series data.
• Knowledge of learning from sequences (transformers, self-supervised pre-training, embeddings).
• Proficient Python and SQL for data extraction and experimentation.
• Ability to explain complex ideas to audiences outside your field.
• Bonus: experience with recommendation systems or user behavior data.

Responsibilities

• Build our first behavior model turning raw session events into embeddings of visitor behavior.
• Identify buying intent during sessions and group visitors into audiences for personalized page versions.
• Review new research papers, try methods on Shuttlebase data, and publish if valuable.
• Collaborate with engineers and the CTO, guiding modeling decisions and communicating insights to clients.

Skills

Python

SQL

Transformers

Sequence modeling

Time-series data

Education

PhD or equivalent in a quantitative field

Tools

ClickHouse

AWS

Job description

Why Shuttlebase?

Every day, millions of people decide whether to buy something online, and the reasons behind those decisions are still mostly guesswork. We want to change that.

We're working to quantify human psychology: to build an embedding model for human behavior that understands how people react to a page, a price, or a single sentence, and can predict what will work before anyone runs a test.

Every experiment our AI runs on a live store teaches that model something about how people decide. Our goal is for any company to be able to ask, "I'm selling product X to audience Y, how do I optimize for Z?" and get an answer it can trust.

We're early and well funded. The people who join now will pick the tools, design the models, and help choose who joins next. If that's a problem you want to spend the next few years on, we'd like to meet you.

Applied Scientist, Behavior Modeling

Every day our script records tens of millions of actions from people visiting the websites we work with: what they look at, where they hesitate, what they click, and when they leave. You'll turn that into the first version of our behavior model. The goal is a model that predicts how people are likely to interact with a website, and what the site should and shouldn't do for them.

We'll start with online stores, since that's where we work today, by spotting which visitors are close to buying and which groups need to see a different version of the page. Researchers have published a lot about learning from user behavior with sequence models and embeddings, so you won't start from a blank page. Your job is to know that work well, pick what fits our data, get it working here, and keep up as the field moves.

You'd be the first person working on this full time, so a lot rests on your shoulders!

What you'll work on

• The behavior model. Build our first model that turns raw session events into embeddings of how a visitor behaves. Pre-training a transformer on event sequences is a likely start, but you'll make the call. The hard part is that most sessions are short and anonymous, and most visitors never come back.

• Buying intent and audiences. Use the model to spot buying intent during a session and to group visitors into audiences, so the AI can show each audience the page version that works for it. We want a first version on live stores as soon as it works, and we'll improve it from there.

• New research. When a paper comes out that could help, you'll be the one who reads it, tries it on our data, and decides whether we use it. If you learn something worth publishing, publish it.

We mostly work in Python, with event data in ClickHouse and services on AWS. You'll report directly to our CTO, and work every day with our engineers, who build on your model, and with our client team, who explain to stores why the AI showed their shoppers a different page. A lot of what they say will come from you.

You'll love this job if

• You read papers and get impatient until you've tried the idea on real data.

• You'd rather adapt a proven method and see it work in three weeks than spend a year inventing a new one.

• You want a big, open problem that's yours to figure out, with engineers and the founders working right next to you.

• You're fine working with noisy event logs and writing your own SQL to get at them.

• You were the person in your lab others came to when they needed a hard idea made simple.

• You want to help build a model that understands how people make decisions, and you'd like to be there for the first version of it.

What you bring

• A PhD or equivalent research experience in a quantitative field. People from physics, math, computational biology, and neuroscience often fit well, especially if you've modeled behavior or sequences.

• You've trained a model on messy, real-world sequence or time-series data yourself, and you've shown whether it worked.

• You know the recent work on learning from sequences (transformers, self-supervised pre-training, embeddings) well enough to choose between approaches and explain why.

• You write solid Python and can pull your own data with SQL.

• You've given talks or written for people outside your field, and they followed.

• Bonus: experience with recommendation systems or user behavior data, large event datasets, or eCommerce.

What We Value

• Curiosity and excellence: We're trying to understand why people decide what they do, so asking questions is the job. We push on each other's ideas, and a failed experiment teaches us as much as a winning one.

• Whatever it takes: If something needs doing, whoever can do it does it, whatever their title. Our clients' results are our results.

• Ownership: Shipping something is where the work starts. You follow it all the way to the result, and when you get something wrong, you say so and fix it. We keep our promises, the big ones and the small ones.

• Agility: Most ideas go from whiteboard to working prototype in two or three days. If something isn't working, we drop it fast, and nobody holds it against you.

• Enjoy the ride: Building something new comes with rough weeks. We get through them together and celebrate the good ones.

What We Offer

• Competitive compensation

• Meaningful equity - real ownership in Shuttlebase’s success.

• Medical, dental, and vision coverage for you and your family.

• Unlimited PTO - we trust you to take the time you need.

• Tax free commuter and parking benefits

• Office-first culture (4 days/week) - Midtown Manhattan, in the middle of it all.

• Work directly with the founding team - your impact is immediate, visible, and career-defining.

• Free One Medical Membership

• 401k