Senior Data Scientist - eCommerce - IIT/NIT/BITS

Designation: Sr Data Scientist

Location: Bangalore

Experience: 6 - 12 Yrs

Mandatory Skills: Machine Learning, Python

Only Product Based, Ecommerce company candidates will be entertained

Candidates currently in Bangalore should only apply

Roles & Responsibilities:

- The candidate would develop large scale and high-impact data science products to understand and derive insights from the billions of data points collected on the Company's platform.

- Company collects media viewership data across multi-millions of users every single day. Some of the areas that the Data Science team would be involved in: Recommendations to suggest shows, news and allied content across 100 million TV Viewers.

- Build competitive real time Ad-fraud detection systems for the digital-ad ecosystem. Building competitive bidding systems to identify robust and efficient ad-campaign utilisation.

- Build custom demographic characteristics based on media consumption habits and behaviour embeddings

- Multi-level Forecasting algorithms: How many people are likely to watch the IPL game next week, next hour? Which of these users fit a defined psychographic profile?

- Building Automated Anomaly Detection Solutions across businesses.

- Deep Learning Products on Video and Image Processing.

Roles Requirements:

- The candidate is expected to own Data and ML pipeline for projects across the different business units in Company and should have good experience implementing and handling end - to - end data science products (-10's TB of Datasets).

- He is also expected to own periodic model validation and optimization workflows for the data science products developed.

- Should have worked on large scale data heavy projects on user profiling, time series, forecasting models, segmentation, cluster models, campaign optimization, pattern mining / detection, classification/regression modeling, recommender systems and deep learning models etc.

Hands on :

- Organize and "wrangle" large datasets.

- Good understanding of model validation processes and optimizations. 

- Good applied statistics skills, such as distributions, statistical testing, regression, etc.

- Strong hands on scripting and programming experience in Python Great analytical skills and excellent hands on experience in Machine Learning techniques such as Decision Trees (Random Forest), SVM, GBMs, Topic modelling, Regression (Linear & Logistic) and Deep Learning algorithms like CNN, RNN and LSTMs.

- Ability and willingness to go through research papers and implement ideas/algorithms for product/platform development. El Fluency using different machine learning techniques and algorithms, ideally using ML, Deep Learning frameworks & Statistical libraries such as Scikit-learn, Tensorflow, Keras, Pytorch etc.

- Work with engineers to translate models into scalable high-performance engineering systems El Actively involve in envisioning and design discussions of new Al based assets/platforms with product stakeholders N Exposure to Big Data technologies Hadoop, Hive, MapReduce, SparkML

Requirements

Top Characteristics we look for. 

- Great ML, DL and statistical implementations complementing Problem Solving Ability.

- Awesome SQL, data scripting and wrangling skills

- Fast paced, detail-oriented and ability to own the Data Science product pipelines. 

Background: 

- Degree in a relevant study area is required (e.g. computer science, mathematics, operations research, statistics, business analytics, engineering )

- 6 to 12 years of experience in the field of advanced quantitative techniques, data sciences and large scale machine learning while working for leading global academic institutes or corporate innovation research labs or analytics organizations of large corporates or in consulting companies in analytics roles.

Skills :

- Must have Python Programming, ML (Matchine Learning)

Qualifications TOP Colleges, BE/BTech/MTech/, BIT, IIT, NIT

Working Days 5 Days a week

Job Nature Full Time