AI/ML Expert

On-siteMidML Engineerposted 3mo ago

✦Role summaryAI-generated

This role requires building production-grade AI models for automotive applications, blending computer vision and time-series techniques to solve real-world challenges in pattern recognition and predictive analytics. Candidates should prioritize hands-on implementation over theoretical research, with a focus on deploying models in high-stakes industrial environments.

Skills required

Computer vision Time series forecasting Object detection Multi modal learning Deep learning Feature engineering Model validation Automotive ml Anomaly detection AI Time series Data analysis Machine learning

About this role

We are seeking a talented Applied AI/ML Engineer to develop sophisticated models that leverage both visual and time-series data.
In this role, you will focus on designing and implementing advanced algorithms to extract meaningful patterns, make accurate predictions, and solve complex analytical challenges.
Your primary responsibility will be hands-on model development (for deploying in to automotive domain), from data analysis and feature engineering to training and evaluation.
Key Responsibilities: Advanced Model Development Design, build, and validate machine learning models for a variety of complex tasks, including: Computer Vision: Object Detection, Image Segmentation, Facial Analysis, and Classification.
Time Series Analysis: Forecasting, Anomaly Detection, and Classification of sequential data. Multi-Modal Modeling:
Fusing visual and temporal data to create more powerful predictive models.
Algorithm Implementation and train a wide range of models, including Deep Learning architectures (CNNs, Transformers, LSTMs, GRUs) and traditional statistical methods (e.g., ARIMA, Prophet).
Stay current with state-of-the-art techniques and apply them to our unique datasets.
Data Analysis & Feature EngineeringConduct in-depth exploratory data analysis to understand data characteristics and identify predictive signals.
Develop and implement novel feature engineering techniques tailored to both image and time-series data.Model Optimization & Evaluation Focus on building computationally efficient models.
Rigorously evaluate model performance using appropriate metrics and validation strategies to ensure robustness and accuracy.
Optimize model architecture and hyperparameters to achieve desired performance targets.