Machine Learning Engineer at Predata

New York City · Full Time
At Predata, we’ve built a predictive analytics platform that enables customers to anticipate global events and market moves by better understanding human behavior through alternative data and machine learning. Clients across various industries use the Predata platform to discover, quantify, and act upon the risk of future events. Read More
Apply to Predata

Job Description

As a machine learning engineer at Predata, you will work on our core algorithms for extracting volatility signals from raw sources, and their integration into analyst workflows for filtering through and understanding data.

You should be a insatiably intellectually curious. We’ll expect you to take projects from the idea stage to prototype to a finished product — this means proposing, prototyping, proving the utility of, and scaling and instrumenting both models and model evaluation techniques.

Our system takes thousands of discrete sources in every language, turns them into (sometimes nonlinear) time series (often exhibiting severe heteroskedasticity), and forecasts the likelihood of specific types of geopolitical events in times and places in the future.

We've barely scraped the surface of what can be done with our data, and are adding more sources and more data constantly. We've used or tried sparse regression, wavelet theory, proportional hazards models, and a laundry list of other things, but we're excited by the prospect of LSTMs or other Recurrent Neural Network architectures, language independent NLP techniques, ensemble methods for time series, graph-based learning, and other great ideas that pop up as we continue exploring our problem domain.

Our ideal candidate would fit many of the following:

- You have a PhD/MS in Machine Learning, Statistics, CS or a related field, or a B.S in CS, Math, or related, with experience implementing machine learning systems in industry
- You understand the importance of model evaluation/testing techniques and the statistics behind them
- You have experience with time series analysis or a strong regression background along with a good understanding of how time series regression differs from cross-sectional studies
- You are an expert with Python/Scikit-Learn, and you've at least tinkered with Spark MLLib/GraphLab
- You enjoy reading academic papers and implementing systems in your own free time (e.g. Kaggle)

Apply Now

People also viewed

New York City
New York City
New York City

What We're Building

Predata transforms digital conversation and web traffic data into risk signals, market indicators, and event predictions.

Other Jobs at Predata

  • Software Engineering Jobs
    Full-Stack Engineer
    New York City, Manhattan · Full Time · $100k – $130k · 0.1% – 0.6%

Predata Team

Jim Shinn
Co-founded Dialogic, did IPO and then returned to academia. Recruited into USG after 9/11, returned to teach at Princeton and then co-founded Predata.
Riley Goodside
Machine Learning Engineer at @Predata. Formerly @AngelList, @OkCupid and @Verisk Analytics.
Dakota Killpack
Princeton PhD student researching the application of nonparametric Bayesian ML techniques to discover structure in music and music communities
Steven Sklar
Full stack developer who has built, designed, tested, and deployed several multi-tier web applications for investment banks and hedge funds in Python and C#.
Tori Rinker
Director of Marketing and Operations at Predata
See More

Predata Investors

Ashby Monk
Co-Founder @Long Game • Executive Director, Global Projects Center, Stanford University • Studied at @Princeton University @University of Oxford @Sorbonne
Jordy Albert
Recovering VC @MoneyLion