As a Machine Learning Engineer at Huq, you will be at the forefront of leveraging mobility data to decipher patterns relevant to various fields, such as predictive analytics and forecasting for real estate and retail, decision-making in local governments, traffic planning strategies, and foundational research on migration. You will be instrumental in processing and analyzing vast amounts of mobile phone location data and metadata. Your primary responsibilities will include:
- Trajectory Processing: Implementing advanced techniques for noise filtering, stay point detection, trajectory compression, segmentation, map-matching, and travel mode detection.
- Semantic Tagging: Utilizing Point of Interest (POI) data to perform poi-matching and segment classification.
- Behavioural Modelling & Analysis: Developing models for user behaviour classification or prediction, POI interactions, and group-level mobility analysis.
Requirements
Essential
- Proficiency in PyData Stack: Strong experience with data science and machine learning frameworks such as Pandas, NumPy, Scikit-learn, etc.
- Deep Learning Expertise: Hands-on experience in designing, training, and optimizing deep learning models, preferably using PyTorch.
- Supervised Learning: Solid understanding and practical experience with supervised learning techniques, ideally sequence models
- Research Implementation: Ability to read, understand, and implement machine learning models from research papers.
Desirable
- Semi/Unsupervised Learning: Experience with semi-supervised or unsupervised learning techniques.
- Mobility Data Experience: Prior experience working with mobility or other spatial time-series data.
Advanced Degree: Master's or Ph.D. in Computer Science, Data Science, Machine Learning, or a related field.
Benefits
This is a hybrid role, with a mix of office and home working.
We are a talented team of highly capable individuals looking to build the best products on the market. Our culture is one of working hard and with single-minded purpose, not one that maintains a regime of long hours. We prioritise quality and strive for excellence and efficiency. We are always looking to adopt the best possible technologies and run with low technical debt and little attachment to legacy code or infrastructure. Our working environment is friendly, focused and supportive - we work hard but we have fun too.
We support and value the personal and professional development of our employees creating an enjoyable and rewarding environment for all. We provide options, pension, professional training budget and wellbeing allowance.