About Zeus
Zeus was founded to create a technology-driven solution that redefines how retailers, manufacturers, and distribution companies view and manage their supply chains. Whether the challenge involves improving on-time deliveries, scaling operations, or achieving digital transformation, our mission is to empower our customers to gain greater efficiency and control over their supply chains while contributing to a healthier planet.
Our software enables customers to solve problems in real time, gain end-to-end visibility, automate administrative tasks, and reduce carbon emissions. As we grow, we remain committed to developing innovative products and approaches that give our customers complete control over their logistics.
As Zeus continues to scale, we are seeking an experienced Growth Marketing Specialist to lead data-driven marketing strategies focused on acquiring Marketing Qualified Leads (MQLs). In this role, you will prioritise and optimise our lead-generation channels, owning and executing growth strategies and campaigns aimed at generating qualified leads to pass on to the sales team.
About the Role
Zeus Labs is seeking a Data Scientist to join our AI and Data Science team and help develop cutting-edge machine learning models and algorithms for Zeus Freight Command AI. The role involves creating predictive models and implementing algorithms that drive transport efficiency, demand forecasting, and automated carrier assignment. This position is ideal for a data science professional passionate about turning complex, unstructured data into actionable insights to fuel our AI-powered logistics platform.
Responsibilities
- Develop and optimise machine learning models to support modules like demand forecasting, dynamic routing, and carrier optimisation, ensuring models can handle unstructured and noisy datasets.
- Work with Data Engineers to ingest, clean, and structure ERP order data, addressing data inconsistency and quality issues to ensure robust model performance.
- Perform exploratory data analysis (EDA) to uncover patterns, anomalies, and opportunities within logistics and supply chain data, building a foundation for model training and validation.
- Design, implement, and fine-tune supervised and unsupervised learning algorithms to provide predictive insights into order volume, carrier performance, and delivery schedules.
- Collaborate with Product Managers and Engineers to translate business objectives into data science initiatives, ensuring alignment with our AI-driven product roadmap.
- Validate model accuracy, precision, , and perform error analysis to ensure high-quality predictions.
- Develop documentation and tools for model interpretability and reproducibility, enabling effective communication of model results to non-technical stakeholders.
Qualifications
- Bachelor’s or Master’s degree in Data Science, Statistics, Machine Learning, or a related field;
- Strong proficiency in Python (Pandas, Scikit-Learn, TensorFlow, PyTorch) and SQL for data manipulation and model development.
- Good understanding and application of statistical concepts
Experience
- 4 to 5 years of experience in data science, focusing on data wrangling and handling unstructured data and data cleaning.
- Hands-on experience working with unstructured data and knowledge of best data cleaning and transformation practices
- Experience with ERP data or similar systems is a plus, particularly in integrating ERP data with machine learning pipelines.
- Significant experience with AWS services (AWS SageMaker, S3, Lambda, Redshift) for scalable model deployment.
- Experience with pre-trained AI models from providers like Nvidia, OpenAI, and Microsoft is valuable.
- Strong communication skills and the ability to explain complex models with presentation layer equivalent to Power BI or the AWS and insights to diverse audiences.
Application Requirements
Please submit a cover letter outlining
- your relevant experience
- motivations for applying
- reasons to believe you're well-suited for working with enterprise clients to manage and optimise data from legacy ERP systems.
