Sr. Data Scientist - Medical Imaging *** 90-120/hr W2 *** Direct End Client ***

data science, statistics, machine learning models, deep learning networks, python, spark, pyspark, TensorFlow, Artificial intelligence, Leadership, Apache Spark, Machine learning, Health care, Deep learning, Pharmaceutics, Computer science, Software development, Mathematics, 2D computer graphics, 3D computer graphics, Advanced analytics, Algorithms, CNN, Computational science, Data engineering, Data management, DICOM, Computer vision, HPC, Life sciences, Medical imaging, PyTorch, RWD, scikit-learn, NumPy, Keras
Contract W2, Contract Corp-To-Corp, 12 Months
$90 - $120
Travel not required

Job Description

Immediate direct end client requirement. Remote work till 5/31


  • Support and contribute to the development of advanced analytics, computer vision, and computational tools to derive novel imaging based biomarkers
  • Collaborate with internal imaging- and data scientists and external vendors to derive and validate novel imaging biomarkers in support of clinical drug development and RWD evidence (payer support) generation
  • Curate/clean/organize large and messy clinical imaging datasets
  • Identify and support imaging data management solutions
  • Continually search for opportunities to automate workflows and streamline processes

Required Skills

  • In-depth knowledge and coding experience in Python (polyglot in multiple programming languages a plus). Hands-on skills in Data Science packages, for instance Pandas, Scikit-learn, and/or numpy, a must.
  • Extensive experience with commonly used Deep Learning models (2d/3d CNN, LSTM/GRU, etc), modern DL architectures (Resnet, U-net, etc), and frameworks (Tf, pytorch, keras, etc). Hands-on on other ML algorithms (RF, GBM, etc) a plus.
  • Familiarity with advances in AI research and related applications in medical imaging, and/or computer vision (eg video).
  • Technical and organizational skills/experience to lead complex, end-to-end ML/DL/AI projects, including typical project stages such as: data engineering, computing/storage resource budgeting, model training, model selection, model evaluation, and communication with other stakeholders.
  • Fluent in using scientific computing environment e.g. unix / linux shell in a HPC cluster on premise or in cloud, to accomplish common development tasks (eg. editing, testing, efficient debugging, etc.) Hands-on experience with productivity toolchains (eg JIRA, enterprise git.)
  • Understand the practical aspect of the mathematical foundation of ML, in particular optimization (first order method eg gradient descent, second order method eg Newton-Raphson, why in DL first order is dominant). Understand the practical aspect of statistics (population vs sample, different sampling techniques, etc)
  • PhD or MS in relevant quantitative field (CS, EE, Physics, Mathematics, Statistics, etc.), and/or adv. Life Sciences degree with significant computational experience
  • >3yr post-graduate work-experience in fields such as engineering, research, or product development with responsibilities relevant to position.
  • Publications in the areas of Deep-/Machine Learning, and/or Statistics a plus.
  • Solid understanding of medical image data formats (eg DICOM)
  • Excellent communication skills


Posted By

Santa Clara, CA, 95050

Dice Id : 10126850
Position Id : S-DATA-ML
Originally Posted : 2 years ago
Have a Job? Post it