Machine Learning Engineer I

Responsibilities:
Implement forecasting and time-series models (LSTMs, Transformers, TCNs).
Contribute to spatial and spatiotemporal modelling using grid/H3-based systems or graph methods.
Support feature engineering and data preparation for large-scale temporal and spatial datasets.
Help build training pipelines for high-volume mobility and logistics data.
Develop clean, production-ready Python code for training and inference.
Assist in deploying real-time model endpoints and monitoring their performance.
Run experiments and track results across multiple model iterations.
Support model evaluation, baseline improvement, and error analysis.
Work with senior engineers to implement monitoring and drift detection.
Work closely with data engineering to ensure high-quality datasets.
Coordinate with backend teams to integrate ML components into microservices.
Participate in design discussions and contribute to documentation.
Requirements:
0.5-2 years of experience in ML engineering, or strong academic/internship projects.
Exposure to time-series, forecasting, or geospatial modelling.
Strong foundation in machine learning and deep learning frameworks (PyTorch/TensorFlow).
Good understanding of temporal or spatial data processing.
Proficiency in Python and familiarity with data engineering workflows.
Basic understanding of model evaluation and experimentation practices.
Ability to learn quickly and work through ambiguity.
Strong analytical skills and attention to detail.
Clear communication and willingness to work across teams.
Experience working with geospatial systems (H3 quadtrees, maps, mobility datasets).
Exposure to distributed data systems, ML pipelines, or feature stores.
Prior work on forecasting models or mobility/logistics datasets.
Experience contributing to production deployments.

Experience
1-5 yrs