Applied Scientist (LLM/Geospatial AI)

Location: Madrid, Spain

Company

hirify.global develops navigation and location technology through its Navigation Intelligence product engineering organization.

What you will do

• Research and design interfaces that enable LLMs to retrieve, reason over, and use structured and geospatial data.
• Develop AI-ready representations of location data, including geospatial embeddings, knowledge graphs, and structured context formats.
• Define evaluation methods, benchmarks, factuality and hallucination metrics, and datasets for location-grounded AI tasks.
• Design, train, and fine-tune machine learning and deep learning models using large-scale, multimodal data.
• Frame high-impact scientific problems with product managers and stakeholders, including clear success metrics.
• Turn research prototypes into production-quality solutions with AI and software engineers, balancing accuracy, latency, cost, and scalability.

Requirements

• Bachelor’s, Master’s, or PhD in computer science, machine learning, statistics, mathematics, physics, or a related quantitative field, or equivalent professional experience.
• Strong foundations in machine learning, deep learning, statistics, and optimization.
• Hands-on experience with PyTorch or JAX and the Python scientific stack, including NumPy, pandas, and scikit-learn.
• Experience with LLMs and generative AI, computer vision, time-series forecasting, graph neural networks, or reinforcement learning.
• Experience with large-scale datasets, distributed computing, and cloud ML platforms such as Spark, Databricks, Azure, AWS, or GCP.
• Ability to design experiments, define meaningful metrics, communicate complex technical ideas, and write maintainable production code.

Nice to have

• Publications at top-tier venues such as NeurIPS, ICML, CVPR, or KDD.
• Experience with geospatial, mapping, mobility, or sensor data.

Culture & Benefits

• Opportunities to share knowledge with technical and non-technical audiences and contribute to a scientific culture.
• External publications and patents are encouraged.
• Access to hackathons, developer days, and learning programs.