José Manuel Fernández Jaramillo

Scientific Software Engineer building real-time simulation and machine-learning systems

20+ years of experience developing operational forecasting, numerical simulation and data-driven systems in research environments. Now transitioning these skills into industry and deep-tech applications.

Simulation · Machine Learning · HPC · Data Pipelines · Real-time Systems

About

I am a Scientific Software Engineer with a background in geosciences and more than 20 years of programming experience. For almost two decades I have been developing operational numerical modelling and machine-learning systems for coastal and ocean environments at the Coastal Research Laboratory of Kiel University.

My work sits at the intersection of scientific computing, machine learning, and production software engineering. I design and implement end-to-end systems that combine numerical simulation, real-time data ingestion, and predictive models.

Over the years, I have built systems that integrate satellite data, meteorological measurements, ocean sensors and numerical models to produce real-time forecasts of waves and water levels. These systems required robust software architecture, high-performance computing, automated data pipelines and reliable deployment.

Although my career has been in research, most of my work has been engineering-driven and production-oriented: designing software, building infrastructure, integrating heterogeneous data sources and delivering operational tools used by scientists and project partners.

I am currently looking to transition into industry, where I can apply my experience in:

• Scientific and simulation software
• Applied machine learning for physical systems
• Data pipelines and real-time processing
• High-performance and distributed computing
• Engineering of complex technical systems

Selected Achievements

During my work at the Coastal Research Laboratory, I have contributed to the design and development of multiple operational and research systems, including:

• Designed and developed real-time systems for short-term prediction of water levels and waves based on numerical models and machine learning.
• Integrated multiple data sources including meteorological data, satellite imagery and in-situ sensors.

• Developed neural network models to improve hydrodynamic and wave predictions.
• Applied machine learning to optimize fish production processes.

• Implemented data assimilation techniques such as 4DVar and Ensemble Kalman Filters to improve model accuracy.
• Worked with numerical models of hydrodynamics, waves, sediment transport and water quality.

• Led the design and deployment of a Linux HPC cluster for simulations and data processing.
• Optimized workflows for large-scale numerical modelling and data analysis.

• Designed and developed a prototype autonomous boat for bathymetric measurements integrating telemetry, GPS and sensors.

What I Can Bring to Industry

My experience in research translates directly into industrial applications in deep-tech, climate tech, energy, maritime technology and data-driven engineering.

I can contribute to:

Development of numerical and hybrid simulation systems for physical processes and engineering applications.

Design of machine learning solutions for time-series forecasting, sensor data, anomaly detection and hybrid physics-ML systems.

Building pipelines that ingest, process and analyse data from sensors, APIs and large datasets.

Development and optimization of computational workflows using Linux, clusters and parallel processing.

End-to-end development of systems combining hardware, software, modelling and data.

Open to Opportunities

I am currently seeking opportunities in industry where I can contribute to challenging technical problems and continue >

If you think my profile could be a good fit for your team, feel free to get in touch.