ABOUT KEEPER

We're a YC startup that uses a combination of great UX and heavy-lifting data science to save freelancers from the headache of 1099 taxes. We have:

• 30,000 paying users (subscription price: $200 / year)
• 10K reviews on the App Store and Play Store (average: 4.8 stars)
• 23 employees (Series A)

ABOUT THE ROLE

We're looking for a machine learning intern to help us build user-friendly features powered by LLMs. Here are some examples of projects we’re currently working on:

• Building a form differentiator that classifies uploaded PDFs by form type (e.g., 1099-NEC for freelance income, 1099-B for investments, etc)
• Tuning LLM-based assistants that answer product questions (e.g., "where do I put my W-2?") and tax questions (e.g. “can I write off my rent if I have a home office?”)
• Iterating on our core ML models: a classification model to predict which transactions are tax-deductible, and an NLP model to generate human-readable transaction descriptions

RESPONSIBILITIES

• Design and execute experiments using Python, Pandas, Weights & Biases, MySQL, and LLMs
• Train, test, and deploy state-of-the-art machine learning models in production
• Work with senior data scientists to find technical solutions for complex business problems
• Have excellent written communication skills (experiment write-ups, code reviews)

LOCATION/DURATION

• We have a mix of remote and in-office employees. We are looking for someone who wants to work a few days per week in our SF office (Hayes Valley)
• This is a ten-week position, expected to start in September 2023