AI ML Consultant - Automotive Applications

Role Overview:

We are seeking an experienced AI/ML Consultant to collaborate with automotive engineering teams at MSIL (Computer aided engineering (CAE), design, testing etc) and develop Machine Learning models in key domains as per requirements. The ideal candidate will have strong expertise in AI/ML algorithms using time-series (sensor), audio or image data, data generated using CAE. Understanding automotive engineering concepts & CAE tools (Lsdyna, MSc Nastran etc), Finite element method (FEA) will be added advantage. Engagement is being considered for a period of 1 year (extendable to 1 year, based on requirements & outcomes)

Key Responsibilities

. Work closely with Engineering teams to identify opportunities for applying ML techniques.

. Develop, train, and validate ML models for predictive analytics in various domains.

. Implement algorithms such as Principal Component Analysis (PCA), Linear Regression, Decision Trees (LGBM, XGBoost,etc), Ensemble Modeling, Neural Networks (GNN ,CNN PINN etc), Auto-encoders, LSTM.

. Optimize models for accuracy, scalability, and integration with existing processes.

. Implement algorithms like sklearn,pygad, etc) for design optimization using ML models.

. Analyze large-scale simulation/sensor (time series), audio, image datasets and extract meaningful insights.

. Document methodologies and provide technical guidance to engineering teams.

. Suggest computational requirements including data generation model training (including GPUs)

. Provide Hardware / Computational requirements (Training & Deployment) for bespoke Solutions aimed at providing Detection, Classification and Inferencing using Audio, Image or Video data.

. Manage model deployment & continuously augment ML models with new data to improve accuracy and robustness.

Required Technical Expertise

. Strong proficiency in Python & ML libraries (TensorFlow, PyTorch, Scikit-learn, etc.).

. Hands-on experience with Linear Regression, Decision Trees (LGBM, XGBoost), Ensemble Modeling, Neural Networks (CNN, GNN), ), Auto-encoders, LSTM

. Knowledge of data preprocessing, feature engineering, and hyperparameter tuning, cross validations.

. Experience with GPU computing, model deployment, and scalable ML pipelines.

. Ability to create visualization tools & interface for ML model usage.

Preferred Skills

. Familiarity with CAE tools terminology (Crash, NVH, Durability simulations) and experience in working with time-series data is a significant advantage.

. Understanding computing requirements for data generation & training of different models, experience in suggesting requirements for GPU configurations.

Key Performance Indicators (KPIs)

Model Accuracy & Performance - Achieve target accuracy and robustness for predictive models.

Integration Efficiency - Successful integration of ML models into current workflows. Computational Optimization - Efficient use of GPU and HPC resources for training and deployment.

Data Augmentation - Timely updates and retraining of models with new simulation data.

Collaboration Impact - Skill up of MSIL engineers in data handling & ML model development and integration.

Project Timelines - Delivery of ML solutions within agreed timelines.

Qualifications

. Any Bachelor's/master's degree (preferred in engineering, computer Science/Data Science.) with experience in AI/ML model development, deployment & continuous augmentation. Automotive or CAE domain exposure will be preferred.