Objectives of this Role
Design and implement machine learning, information extraction, probabilistic matching algorithms and models for the core Ascendo.ai predictive analytics application.
Work closely with data scientists to design and implement rule-based or algorithm-powered insights based on multiple disparate data sources.
Get exposed to NLP, Time Series and multivariate data sets and share ideas to improve existing models.
Deciding on ML experiment setup that has to be run this would include things like how to divide the feature set, how to evaluate the results, deciding on which ML model to use and how to tune it
How to design, build and maintain data pipelines for supporting the ML models
Understanding all data sources in detail, design and implement machine-learning algorithms that work around the imperfection of the data and help the data team to improve the data quality and coverage.
Contribute to the design and implementation of a validation framework for productized machine learning algorithms.
Collaborate effectively with team members and product management.
Be part of a fast paced agile team.
Daily and Monthly Responsibilities
We’re looking for someone who has an interest in machine learning architecture, with a passion for getting things done. You also like to learn new things. And you want to work with smart people and have fun building something great. You will want to explore uncharted territories and be comfortable with it to build scalable machine learning solutions that can work with large sets of disparate data sources and make sense of the complexity.
Skills and Qualifications
Strong computer science fundamentals including data structures, algorithms, and computer architecture.
String experience in data modeling with the goal of finding useful patterns
Experience in Scala, Java, C++, Python, or other equivalent languages commonly as well as one of frameworks like SparkML, TensorFlow.
Solid engineering and coding skills. Ability to write high performance production quality code.
Excellent understanding of common families of models, feature engineering, feature selection and other practical machine learning issues, such as unbalanced data, data sparsity etc.