About the role
Data Scientist
Location: Cape Town (Remote)
Our client, a dynamic UK-based tech startup is seeking a Data Scientist to help transform complex geospatial and radar data into actionable insights that enhance transport and logistics operations for global brands and public-sector clients.
This fully remote opportunity offers the chance to collaborate with an international team, contribute to groundbreaking machine learning initiatives, and grow within a fast-paced, venture-backed environment.
Introduction
Are you passionate about leveraging data to solve complex, real-world problems?
Our client is looking for a skilled Data Scientist to lead the development of advanced machine learning models and geospatial analytics that power smarter transport and logistics solutions.
If you have experience with spatial data, radar analytics, and predictive modeling and thrive in an innovative startup environment where autonomy, creativity, and technical depth are valued this role is your opportunity to make a tangible impact.
You'll join a collaborative team bridging the UK and South Africa, turning rich sensor and geospatial datasets into intelligence that drives meaningful operational improvements for top-tier clients and major government agencies.
Key Responsibilities
Design and develop machine learning models to analyze geospatial and radar data for transport and logistics applications.
Translate complex datasets into actionable insights that optimize vehicle and people movement across public and private sectors.
Collaborate with UK-based leadership and South African technical teams to design and implement innovative data-driven solutions.
Continuously improve data collection, processing, and predictive modeling methods to enhance performance and accuracy.
Manage the full data science lifecycle from problem definition and model development to deployment and performance monitoring.
Thrive in a fast-paced startup environment, iterating quickly and refining solutions based on client feedback.
Contribute to building and scaling the data science function, with potential to lead and mentor future team members.
Qualifications and Skills
Bachelors, Honours, Masters, or PhD in Statistics, Mathematics, Computer Science, Engineering, or related field.
3 - 5 years of professional experience in data science, including end-to-end project delivery.
Proven expertise in machine learning (e.g., linear regression, XGBoost) and predictive modeling.
Proficient in Python and SQL, with experience in Google Cloud Platform (GCP) or similar.
Hands-on experience with geospatial data, GIS, or radar analytics is highly advantageous.
Strong analytical and problem-solving skills with technical depth and minimal client-facing focus.
Comfortable working in an agile startup setting with fast iteration cycles and evolving priorities.
Excellent collaboration and communication skills, able to translate complex technical insights effectively.
Core Skills & Experience
Machine learning & data science: Building and validating classification/regression models; applying precision/recall, confusion matrices, and error analysis to drive improvements.
Python expertise: Strong experience with ML, data processing, and visualisation libraries (scikit-learn, PyTorch, pandas, matplotlib, plotly, etc.).
Sensor data handling: Comfortable working with spatial time-series data (radar point clouds, GPS, UWB, accelerometer, etc.).
Visualisation & dashboards: Translating outputs into actionable insights via plots, overlays, and interactive dashboards.
Cloud data engineering: Experience with cloud platforms (Azure, AWS, GCP) for data ingestion, storage, and analytics (e.g., IoT Hub, S3, Pub/Sub, CosmosDB/BigQuery).
Collaboration & documentation: Effective cross-disciplinary communication; producing reproducible code, pipelines, and well-documented results.
Preferred Skills & Experience
Radar data: Exposure to radar sensors and features (RCS, Doppler, track stability) a strong advantage.
Data fusion: Combining multiple sensor data streams (radar, video, GPS, UWB) into coherent datasets.
Contextual data integration: Enriching sensor data with external sources such as weather, points of interest, events, and demographic data.
Geospatial data: Experience with maps, coordinate systems, overlays, and spatial/temporal data joins.
Cloud-native pipelines: Deploying ML/data pipelines using serverless functions, containers, and workflow tools (e.g., Azure Functions, AWS Lambda, GCP Dataflow).
Scalable storage & analytics: Handling large datasets using distributed processing and query engines (e.g., SQL, Spark, Databricks).
Ready to Make an Impact?
If youre ready to transform geospatial and radar data into meaningful insights that drive smarter, more efficient transport and logistics solutions, our client wants to hear from you.
Join an ambitious, globally connected team where your machine learning expertise will directly shape real-world outcomes and accelerate innovation in the data science space.
Originally posted on Himalayas