AVP/SM Data Scientist For Goods & Service Tax Network, Delhi

from 8 to 13 year(s) of Experience
Delhi

Job Description

AVP/SM – Data Scientist


Reporting to:Head, Business Intelligence and Fraud Analytics

Function:Technical

Role:Data Scientist

Experience:8+ Years

Location:Delhi


Role Description

We are looking for a hands on Data scientists to handle challenging problems in the areas of Indirect Tax Fraud & Analysis using cutting edge data science techniques. You have engineering skills to work with structured and unstructured data. You have applied knowledge in statistics, machine learning and NLP systems. You will be a machine learning expert who will co-create our implementation playbook of our machine learning / deep learning / NLP / AI capabilities. You have sound experience on machine learning, excellent communication skills and constantly keep pace with industry trends and new technologies. You have a passion for conceptualization, prototyping, debugging & developing ML-based products, applications & solutions.

Key Responsibilities

  • Leads discovery processes with stakeholders to identify the business requirements and the expected outcome.
  • Collaborates with subject matter experts to select the relevant sources of information.
  • Design and build analytic solution for our customers in short development cycles.
  • Designs experiments, test hypotheses, and build models. Conducts advanced data analysis and designs custom algorithms.
  • Creates visualizations, dashboards and reports to explain insights to the stakeholders.
  • Presents and depicts the rationale of their findings in easy to understand terms for the business.
  • Demonstrated data science experience with both structured and unstructured data.
  • Knowledge of statistical techniques (ANOVA, Chi squared, Correlation etc) to design, test and validate hypothesis.
  • Experience working with classical machine learning models: Bayesian models, Tree based models, Margin based classifiers, Boosting and Bagging models, Cluster analysis, and Anomaly detection systems.
  • Expert in feature engineering and evaluation
  • Hands on experience in handling text data using NLP techniques (e.g. document classification and clustering, topic mining, linguistic analysis, entity recognition, semantic search, information retrieval).
  • Knowledge of classical time series analysis techniques e.g. Holt-Winters, ARIMA.
  • Some Data visualization experience ( Tableau, Qlikview, D3.js etc)
  • Experience working with new generation ML algorithms (eg: SVM; LDA; Kernel Based Models; Decision Trees; GBM; NN; Rule mining; Pattern Discovery etc)
  • Some experience with Deep Learning models and their applications for CV; NLP and time series forecasting
  • Experience and interest with privacy preserving techniques, hyperparameter optimization, model tuning and optimization
  • Experience in designing end to end ML workflow and developing the modeling code to agreed engineering specs
  • Knowledge distributed data science techniques, methods and tools
  • Knowledge of model testing and post production drift, bias and shift detection
  • Ability to write efficient, concise and maintainable code

Others

Learn new technologies & tool and suggest better ways of improving data science operations

Design, Discuss with Senior Management & Own your personal & professional development plan

Create, Discuss & work through a training plan in the area of your interest which aligns with current & future responsibilities

Key Interfaces

External:

Internal:

External stakeholders (tax authorities, taxpayers, treasuries, banks, policy makers, process groups, etc.)

Internal departments i.e. Technology, Strategy, MIS & Analysis, Services team and CISO

Key Attributes & Skills:

Basic Qualifications:

Experience of 8+ years as a Data Scientist. Graduate with any STEM field

Core Skills:

Analytics software/programming technologies: Python, SparkML, Tensorflow, Big DL, Horovod, H20, Rapidminer, R, CPLEX, LION

Database technologies: MySQL,MongoDB, Hadoop ecosystem, couchdb, redis, neo4j

ETL technologies: Python, Spark

Languages: Python, Pyspark, Scala, Java Script, UNIX Shell; Django

Data Visualization: Bokeh, Dash, Seaborn, Tableau, D3.js

Statistical Methods: Probability distribution, ANOVA, Factor Analysis, Correlation & Regression, Conjoint, Time series, DoE, Sampling, PCA, Statistical Inference, MCMC

Machine Learning Methods/Algorithms: CHAID, Bayesian models, Linear & logistic Regression, SVM, RVM, Neural Nets, K-means, Expectation maximization, DBSCAN, BIRCH, Ensemble models, ICA, LDA, Graph models, Anomaly Detection models, xgboost, LSA, Lasso, Ridge, Elasticnet, Constraint & Multi-objective programming

Cognitive & NLP: CoreNLP, NLTK, CNTK ; GENSIMl Spacy

Deep Learning: Tensorflow; H2O; Pytorch; Horovod; Caffe; Big DL

Specific Packages: Scikit-learn; Pandas; numpy, PySpark, matplotlib, bokeh, seaburn, R-shiny, ggplot2, Alchemy, Dask, Big DL, Horovod, Distributed ML

Big Data Tools: Spark, Hadoop, Hive, HBASE, Hue, Drill, Presto

Additional Skills (Good to have)

Working knowledge of Spark & Hadoop ecosystem

Experience of Financial Crime modelling

Experience in K8 based ML workflow tooling

Salary: Not Disclosed by Recruiter

Industry:IT-Software / Software Services

Functional Area:IT Software - Application Programming, Maintenance

Role Category:Project Management

Role:Project Manager-IT/Software

Key Skills

Desired Candidate Profile

Please refer to the Job description above

Education-

UG:B.Tech/B.E. - Any Specialization, B.Sc - Maths, Computers

Company Profile

NISG (National Institute for Smart Government)

www.nisg.org
View Contact Details+

Contact Company:NISG (National Institute for Smart Government)