Job Description
- Hyderabad, Telangana, India
Company Description
They help the world see new possibilities and inspire change for better tomorrows. Their analytic solutions bridge content, data, and analytics to help business, people, and society become stronger, more resilient, and sustainable.
Job Description
About the Role:
The research team at Verisk EES (Extreme Event Solutions) works on innovative research in AI for climate risk. They are looking for highly talented and motivated candidates passionate about doing industrial R&D, building, and deploying AI and ML solutions for real-world problems. You will play a critical part in expanding their model capabilities to improve their understanding and predictions of climate extremes and enhance the view of risk they provide to their clients. In this role you will be responsible for building, deploying, and validating machine learning algorithms to solve real-world climate problems, focusing initially on atmospheric-perils modeling. This role is a perfect blend between machine learning and climate science, and you will find in it many opportunities to express your technical skills and creative mindset.
About the Day-to-Day Responsibilities of the Role:
- Design, build, deploy, and maintain machine learning models to achieve research and business objectives of the Research department.
- Collaborate with and provide support to other research groups to develop new machine learning tools and enhance existing models.
- Evaluate model performance on real-world data and present findings to key decision makers.
- Identify appropriate data sources and process, clean, and verify integrity of data used for analysis.
Qualifications
- Ph.D. degree (completed or close to completion) in engineering fluid mechanics, atmospheric science, computer science, statistics, or a related field is must.
- 2+ years of experience building machine learning models in industry or academia.
- Publications in relevant top-tier journals / conferences is preferred.
- Good theoretical understanding of the physical processes governing climate phenomena and fluid dynamics (turbulence, convection, closure models, etc.)
- Strong command of machine learning algorithms for spatiotemporal data and physical processes (LSTM, TCN, CNN, Transformers, PINNs, Neural Operators etc.)
- Experience with common data science toolkits such as scikit-learn, PyTorch or TensorFlow is must.
- High degree of comfort deploying machine learning models in a HPC environment.
- Experience with Generative models (GANS, Diffusion models) is a plus.
- Excellent verbal and written communication skills, including the ability to convey technical ideas to a non-technical audience.
- Team-focused and evidence of supporting project team members.