Infotainment Engineer
Stefanini Group is hiring!
Stefanini is looking for Infotainment Engineer, Dearborn, MI (Hybrid)
For quick apply, please reach out to Pawan Rawat at 248-213-3605 /pawansingh.rawat@stefanini.com
Position Description:
As a Software Engineer working in the In-Vehicle Infotainment, you will have the responsibility of designing and developing Artificial Intelligence (AI) Systems for Software Quality and Warranty. In this role, you will lead the development and maintenance of AI and machine learning algorithms to measure and identify the performance of Infotainment systems.You will own delivery of highly stable and high-quality product. Our infotainment systems must be equipped to handle the use cases of today and those of tomorrow. Our ambitions reach well beyond existing solutions, and we are in search of innovative individuals to join this team.
Ideal candidates will have experience in artificial intelligence and machine learning and big data analytics and delivering such a trained system. Candidate should have excellent interpersonal and communications skills. Success in this role requires someone who is centered around product and engineering excellence with a bias for action; thrives in a fast-paced, dynamic environment; successfully partners with a wide group of people at multiple levels of the company; and embodies our practices for diverse teams.
Skills Required:-
Bachelor's degree in computer science, electrical engineering, mathematics, statistics, operations research, or related field -
Experience with the complete software lifecycle for embedded systems -
Strong technical writing and oral communication skills -Demonstrated contributions and expertise in two or more of the following domains: o Regression algo for interpolation and extrapolation (both linear / non-linear) o Time series analysis and statistics, autoregressive models, filtering algorithms o Gaussian processes and/or kernel methods, Bayesian statistics o Modeling with different neural network architectures: MLP, CNN, RNN o Quantitative model performance assessment using cross-validation, blind testing.
o Physics-informed neural networks (ML for computational fluid dynamics or finite element analysis, point cloud or mesh-based neural networks, PDE surrogate modelling) o Uncertainty quantification and propagation for time series analysis and forecasting.