Senior Data Scientist

Published 

Why is this job for you?

We are focused on discovering new patterns in big data. These pattern discoveries will significantly and positively impact people lives. Our initial work is in the biomedical space, focusing on identifying the patterns related to breast cancer, lung cancer, and other diseases such as Chron’s disease. This job is for you because we are taking on what has been viewed as an intractable problem. We learn daily from each other in the space of mathematics, machine learning, data science, bioinformatics and biology, with each of our are experts working at or beyond the state of the art. Learning, sharing ideas, and synthesizing information is our passion. Making a positive impact by combining leading-edge research with emerging technologies is our mission. That’s why we are here. We’ll take on additional domains such as finance, transportation, energy, etc. as time and resources allow.

You are well suited for this job because you have experience working with large data sets. You can scan the data sets and identify the specific nature of the data: floats, doubles, ints, char, string and mixed values. You identify the shape of the data along with the sparsity, density, and note inconsistencies. You see empty values and wonder what it means — Is that zero, or some other indicator? You are familiar with the challenges of ingesting new data sets. If you see missing values, you know how to figure out a way to classify the data with integrity, and not lose the row. You take pride in knowing how to resolve noise in the dataset while retaining the signal strength. Most importantly, you know that many of these datasets contain data that can be used to solve some of the hardest challenges in biomed. Success here can have positive outcomes for those suffering from disease.

Key Responsibilities

  • Collaborate with our mathematicians to identify the right approach and algorithms to understand the datasets. Techniques include dimensionality reduction using established and novel algorithms. You will analyze the datasets, the metadata, and how the algorithms and hyperparameters affect the data and the relationships within the dataset.
  • Work closely with our bioinformaticians and experts in computer science to understand data ingestion techniques, data validation, and noise reduction filters. You will play an integral part in working with the bioinformaticians, mathematicians, and computer scientists on methods to improve the result sets.
  • As a data expert, you will guide our thinking and develop our data handling practices. You will be our point person working closely with our partners to provide source datasets to our company. You will find methods to improve the quality of the source data, and will work with our domain experts to evaluate and understand the result sets.
  • You will select methods to condition the data and help determine which statistical and mathematical methods to use in the data processing workflow to improve results.
  • Collaborate across the product management, science, engineering, program management teams to understand the needs of the various teams. Identify best practices in our data handling and processing methods to have implemented as reusable libraries in pattern discovery, detection and recognition.
  • Expand your own abilities by learning some of the adjacent areas in which you are working: machine learning, bioinformatics, biology, or future areas of pattern discovery.
  • Participate in the company’s roadmap planning, key areas of research, investment, and aspirational thinking.

Required Qualifications

  • B.S. (with at least 10 years’ experience) or masters (with at least 7 years’ experience) in Applied Math, Statistics or Computer Science.
  • 7+ years practical experience with SAS, ETL, data processing, database programming and data analytics.
  • Extensive background in data mining and statistical analysis.
  • Able to understand various data structures and data transformation methods.
  • Excellent pattern recognition and predictive modeling skills.
  • Excellent written and verbal communication skills for coordinating across internal and external teams.
  • Experience programming in Python or R.
  • A passion to learn and master new technologies and techniques.

Preferred Qualifications

  • Experience in developing pattern discovery methods.
  • B.S in Mathematics.
  • Knowledge of a variety of machine learning techniques (clustering, decision tree learning, artificial neural networks, deep learning).
  • C++ programming experience.

This position reports to our Chief Technology Officer
Is this right for you? Send us an e-mail at careers@patterncomputer.com
Located in Redmond, Washington
Travel is minimal, less than 25%
Pattern Computer is an equal-opportunity employer