Location: Hyderabad/ Bangalore/ Gurgaon

Team: Data Science and Modelling

The Role: Data Science Analyst

S&P Global Commodity Insights is seeking a strong member within Data Science and Modelling team to work closely with our energy market analysts, Data Scientists, Business Intelligence, and IT teams to implement automated workflows; also execute and support the legacy as well as the next generation advanced Data platforms. In this role you will look to play a key role in understanding data and its processes and to assist the design, development, implementation of new technological advancements aligning with the CI Tech strategy.

What We’re Looking For:

We are looking for a process orientated, methodological thinker with a keen eye for detail, who has proven experience working and leading structured workflows leveraging Data science technical skills. This role would be ideal for someone proactive and eager to learn about various commodity markets, deal with large sets of data and be able to transform it to the Analytical needs of the organization by leveraging advanced Data Science skills and capabilities.

Responsibilities:

• Ability to understand problem statements and implement analytical solutions & techniques independently being proactive and thought leadership aligning with the Data Science and Modelling team strategy.

• To be able to convert excel models into python models.

• To be able to conceptualize, design, and deliver high-quality framework solutions.

• To leverage technology and integrate new transformed datasets into the data pipeline architecture.

• To work closely with various stakeholders and key technology partners to understand data, collect, clean, transform, validate, and visualize datasets.

• To identify and manage dependencies and risks across various analytics datasets, products, and applications.

• To collaborate and coordinate with internal teams and establish operational assistance to provide analytical support of various commodity datasets.

• To be able to understand market data and apply business metadata to new and existing pipeline data flows and help us deliver market relevant analytics content to internal users, external users and products.

• To be able to execute with discipline and deliver appropriate documentation.

• To be able find, investigate, resolve, and report issues to the internal and exte nal users.

• Maintain new and existing data change/ transformation request backlog to e sure all requests are tracked and completed.

• Prioritize backlog and ensure our datasets are accurate and up to date.

• Fast learner: ability to learn and pick up a new tool/ platform quickly.

Required Requirements:

• University degree in Science, Mathematics, Economics, Computer Science, Information Technology, Statistics or equivalent

• Proven experience with Data automation using analytical skills

• Expert level proficiency in Python, Spark, SQL and Cloud environment prefe able AWS

• Proficiency in, or willingness to learn, the other language – R or Matlab

• Experience of working on end-to-end data science pipeline: problem scoping, data gathering, transformation, Exploratory data analysis (EDA), extracting insights, visualizations, monitoring and maintenance.

• Ability to retrieve, interrogate, manipulate, and analyse data and presenting findings

• Ability to create efficient solutions to complex problems.

• Strong knowledge and experience working with databases (MS SQL Server, PostgresSQL)

• Excellent communications and strong presentation skills to the wider audience is essential

• Experience of working and leading processes in agile work streams driving data quality and improvements, experience of Visual Studio (VSTS) desirable but not essential

• Problem-solving: Ability to break the problem into small parts and applying relevant techniques to drive required outcomes.

Preferred Requirements:

• Knowledge of various commodity markets

• Knowledge of machine learning, probability theory, statistics, algorithms, NLP and Deep Learning.

• Experience in Unified analytics platforms like Databricks is beneficial.

• Knowledge of deep learning and related toolkits: Tensorflow, PyTorch, Keras, etc