Business Intelligence Specialist

Role: Data Engineer  
Company: PayU

Location: Bangalore/ Mumbai

Experience : 2-5 yrs

About Company:

PayU is the payments and fintech business of Prosus, a global consumer internet group and one of the largest technology investors in the world. Operating and investing globally in markets with long-term growth potential, Prosus builds leading consumer internet companies that empower people and enrich communities.

The leading online payment service provider in 36 countries, PayU is dedicated to creating a fast, simple and efficient payment process for merchants and buyers. Focused on empowering people through financial services and creating a world without financial borders where everyone can prosper, PayU is one of the biggest investors in the fintech space globally, with investments totalling $700 million- to date. PayU also specializes in credit products and services for emerging markets across the globe. We are dedicated to removing risks to merchants, allowing consumers to use credit in ways that suit them and enabling a greater number of global citizens to access credit services.

Our local operations in Asia, Central and Eastern Europe, Latin America, the Middle East, Africa and South East Asia enable us to combine the expertise of high growth companies with our own unique local knowledge and technology to ensure that our customers have access to the best financial services.

India is the biggest market for PayU globally and the company has already invested $400 million in this region in last 4 years. PayU in its next phase of growth is developing a full regional fintech ecosystem providing multiple digital financial services in one integrated experience. We are going to do this through 3 mechanisms: build, co-build/partner; select strategic investments. 

PayU supports over 350,000+ merchants and millions of consumers making payments online with over 250 payment methods and 1,800+ payment specialists. The markets in which PayU operates represent a potential consumer base of nearly 2.3 billion people and a huge growth potential for merchants. 

Job responsibilities:

• Design infrastructure for data, especially for but not limited to consumption in machine learning applications 
• Define database architecture needed to combine and link data, and ensure integrity across different sources 
• Ensure performance of data systems for machine learning to customer-facing web and mobile applications using cutting-edge open source frameworks, to highly available RESTful services, to back-end Java based systems 
• Work with large, fast, complex data sets to solve difficult, non-routine analysis problems, applying advanced data handling techniques if needed 
• Build data pipelines, includes implementing, testing, and maintaining infrastructural components related to the data engineering stack.
• Work closely with Data Engineers, ML Engineers and SREs to gather data engineering requirements to prototype, develop, validate and deploy data science and machine learning solutions

Requirements to be successful in this role: 

• Strong knowledge and experience in Python, Pandas, Data wrangling, ETL processes, statistics, data visualisation, Data Modelling and Informatica.
• Strong experience with scalable compute solutions such as in Kafka, Snowflake
• Strong experience with workflow management libraries and tools such as Airflow, AWS Step Functions etc. 
• Strong experience with data engineering practices (i.e. data ingestion pipelines and ETL) 
• A good understanding of machine learning methods, algorithms, pipelines, testing practices and frameworks 
• Preferred) MEng/MSc/PhD degree in computer science, engineering, mathematics, physics, or equivalent (preference: DS/ AI) 
• Experience with designing and implementing tools that support sharing of data, code, practices across organizations at scale 

About antuit.ai

Antuit.ai is the leader in AI-powered SaaS solutions for Demand Forecasting & Planning, Merchandising and Pricing. We have the industry’s first solution portfolio – powered by Artificial Intelligence and Machine Learning – that can help you digitally transform your Forecasting, Assortment, Pricing, and Personalization solutions. World-class retailers and consumer goods manufacturers leverage antuit.ai solutions, at scale, to drive outsized business results globally with higher sales, margin and sell-through.

Antuit.ai’s executives, comprised of industry leaders from McKinsey, Accenture, IBM, and SAS, and our team of Ph.Ds., data scientists, technologists, and domain experts, are passionate about delivering real value to our clients. Antuit.ai is funded by Goldman Sachs and Zodius Capital.

The Role:

Antuit is looking for a Data / Sr. Data Scientist who has the knowledge and experience in developing machine learning algorithms, particularly in supply chain and forecasting domain with data science toolkits like Python.

In this role, you will design the approach, develop and test machine learning algorithms, implement the solution.  The candidate should have excellent communication skills and be results driven with a customer centric approach to problem solving.  Experience working in the demand forecasting or supply chain domain is a plus. This job also requires the ability to operate in a multi-geographic delivery environment and a good understanding of cross-cultural sensitivities.

Responsibilities:

Responsibilities includes, but are not limited to the following:

• Design, build, test, and implement predictive Machine Learning models.
• Collaborate with client to align business requirements with data science systems and process solutions that ensure client’s overall objectives are met.
• Create meaningful presentations and analysis that tell a “story” focused on insights, to communicate the results/ideas to key decision makers.
• Collaborate cross-functionally with domain experts to identify gaps and structural problems.
• Contribute to standard business processes and practices as part of a community of practise.
• Be the subject matter expert across multiple work streams and clients.
• Mentor and coach team members.
• Set a clear vision for the team members and working cohesively to attain it.

Qualifications and Skills:

Requirements

• Experience / Education:
  • Master’s or Ph.D. in Computer Science, Computer Engineering, Electrical Engineering, Statistics, Applied Mathematics or other related 
• 5+ years’ experience working in applied machine learning or relevant research experience for recent Ph.D. graduates.
• Highly technical:
• Skilled in machine learning, problem-solving, pattern recognition and predictive modeling with expertise in PySpark and Python.
• Understanding of data structures and data modeling.
• Effective communication and presentation skills
• Able to collaborate closely and effectively with teams.
• Experience in time series forecasting is preferred.
• Experience working in start-up type environment preferred.
• Experience in CPG and/or Retail preferred.
• Effective communication and presentation skills.
• Strong management track record.
• Strong inter-personal skills and leadership qualities.

Information Security Responsibilities

• Understand and adhere to Information Security policies, guidelines and procedure, practice them for protection of organizational data and Information System.
• Take part in Information Security training and act accordingly while handling information.
• Report all suspected security and policy breach to Infosec team or appropriate authority (CISO).

EEOC

Objective

Data Engineer will be responsible for expanding and optimizing our data and database architecture, as well as optimizing data flow and collection for cross functional teams. The ideal candidate is an experienced data pipeline builder and data wrangler who enjoys optimizing data systems and building. The Data Engineer will support our software developers, database architects, data analysts and data scientists on data initiatives and will ensure optimal data delivery architecture is consistent throughout ongoing projects. They must be self-directed and comfortable supporting the data needs of multiple teams, systems, and products

Roles and Responsibilities:

• Should be comfortable in building and optimizing performant data pipelines which include data ingestion, data cleansing and curation into a data warehouse, database, or any other data platform using DASK/Spark.
• Experience in distributed computing environment and Spark/DASK architecture.
• Optimize performance for data access requirements by choosing the appropriate file formats (AVRO, Parquet, ORC etc) and compression codec respectively.
• Experience in writing production ready code in Python and test, participate in code reviews to maintain and improve code quality, stability, and supportability.
• Experience in designing data warehouse/data mart.
• Experience with any RDBMS preferably SQL Server and must be able to write complex SQL queries.
• Expertise in requirement gathering, technical design and functional documents.
• Experience in Agile/Scrum practices.
• Experience in leading other developers and guiding them technically.
• Experience in deploying data pipelines using automated CI/CD approach.
• Ability to write modularized reusable code components.
• Proficient in identifying data issues and anomalies during analysis.
• Strong analytical and logical skills.
• Must be able to comfortably tackle new challenges and learn.
• Must have strong verbal and written communication skills.

Required skills:

• Knowledge on GCP
• Expertise in Google BigQuery
• Expertise in Airflow
• Good Hands on SQL
• Data warehousing concepts

What you need to have:

What you will be doing:

As a part of the Global Credit Risk and Data Analytics team, this person will be responsible for carrying out analytical initiatives which will be as follows: -

• Dive into the data and identify patterns
• Development of end-to-end Credit models and credit policy for our existing credit products
• Leverage alternate data to develop best-in-class underwriting models
• Working on Big Data to develop risk analytical solutions
• Development of Fraud models and fraud rule engine
• Collaborate with various stakeholders (e.g. tech, product) to understand and design best solutions which can be implemented
• Working on cutting-edge techniques e.g. machine learning and deep learning models

Example of projects done in past:

• Lazypay Credit Risk model using CatBoost modelling technique ; end-to-end pipeline for feature engineering and model deployment in production using Python
• Fraud model development, deployment and rules for EMEA region

Basic Requirements:

• 1-3 years of work experience as a Data scientist (in Credit domain)
• 2016 or 2017 batch from a premium college (e.g B.Tech. from IITs, NITs, Economics from DSE/ISI etc)
• Strong problem solving and understand and execute complex analysis
• Experience in at least one of the languages - R/Python/SAS and SQL
• Experience in in Credit industry (Fintech/bank)
• Familiarity with the best practices of Data Science

Add-on Skills : 

• Experience in working with big data
• Solid coding practices
• Passion for building new tools/algorithms
• Experience in developing Machine Learning models