Data Science Specialist

You will be responsible for design and engineering aspects of the Machine Learning ecosystem developing life cycle frameworks and delivering state-of-the-art solutions for ML pipelining, deployment and integration with the back-end product. Ensure efficient architecture and low-level design of deep learning-based solutions and high-quality deliverables with focus on innovation, scientific research, experimentation and optimal design.

As a subject matter expert, you will be combining your professional experience and an intrinsic desire for problem solving.

Development and implementation of ML models for product brand extraction based on product name, description and other attributes

Development and implementation of ML-based product matching solutions

Development of text-based product classification tools

Analyze big amount of data from online retailers using statistical techniques to identify patterns

Build ML, statistical and analytical models, forecasting models

Create ML\DL solution and infrastructure

Responsible for statistical analysis and model research to develop an advanced analytical approach to generate the required insights

Design and implement efficient, fault-tolerant Machine Learning flows for processing high-velocity, heterogeneous data, including optimization of Machine Learning workflows for building automated decision systems that provide future predictions

Provide statistical analysis of large and complex datasets and ensure accuracy in analysis

Develop innovative and effective approaches to solve analytics problems

You will fit right in if you have –

8 years of relevant experience in the domain

Bachelor’s degree in Computer Science or equivalent

4+ years’ experience researching and developing ML models for big data analysis

Experience of deep learning in NLP (LSTM, BERT, etc.)

Proficiency with any deep learning framework, Tensorflow + Keras is preferred

3+ years’ experience and deep understanding of text processing techniques and best practices (classification, NER, text ranking)

Python (Pandas, NumPy , scipy, scikit-learn)

Textual data processing libraries (NLTK, GenSim)

2+ years’ experience of training and productionalization of deep learning models

3+ years’ experience of software development in Python

Excellent knowledge of the data science problems, including large scale data and data pipeline management

Excellent presentation skills, communication skills, verbal and written

Expert in using data analytical and modeling tools

Excellent knowledge in using visualization tools

Strong interpersonal skills and a combination of analytical skills, intellectual curiosity, and accountability