With systems in the industry getting increasingly complex and with continued evolution of technology in terms of new materials, structures and process technologies, it is hard to fully understand all the wear-out and failure mechanisms inherent in a new technology prior to commercialization for practical use. For such instances, it is essential to be able to “diagnose” the “health” of a system in real-time from sensor data and use this data to “prognose” or “predict” on when the system is likely to behave abnormally in the future based on certain user defined threshold for acceptable performance. This calls for the need to develop advanced statistical algorithms and / or machine learning techniques that can be used to develop a predictive model which works well for practical scenario under non-ideal conditions where there could be multiple failure modes / mechanisms playing a role at the same time, with correlated failures, varying environmental and operating stress loads etc…
Positions are immediately available for talented candidates with a strong background in Statistics / Machine Learning. The project will require a sound knowledge of probability and statistics theories, in specific, Bayesian Statistics. Knowledge and interest in AI related models for failure prediction would be a big value add.
Suitable candidates should have a Ph.D. Degree from a reputed institution in any field of engineering / science / mathematics / statistics with sufficient expertise and knowledge in statistical modeling and machine learning. Competitive pay package will be provided depending on the skill sets of the applicant and his qualifications. The position is initially open for 8 months till MAR 2021 and can be extended further through other sources of funding, subject to satisfactory performance of the candidate.
For jobs on this site that accept applications from your location / country,