Data Scientist & AI Engineer | ML/LLM Systems | Geospatial Data Engineering

Machine Learning & LLM Engineering
Expertise in developing end-to-end ML and LLM-powered systems, including RAG retrieval, reranking, prompting, tracing and guardrails, as well as deep neural network-based recommender systems and ad copy improvement tools deployed at production scale.

Geospatial Data Engineering
Strong background in geospatial data engineering, including building and owning AWS pipelines for analysis-ready cloud-optimised (ARCO) data cubes, working with xarray, dask, zarr, netcdf, grib, parquet and shapefiles for large-scale geospatial datasets exceeding 5TB.

Cloud & Data Infrastructure (DevOps/MLOps)
Proficiency in cloud and data infrastructure tooling including AWS, CI/CD, Docker, GitHub Actions, FastAPI, Airflow, Spark, Snowflake, MLflow and Metaflow, enabling robust deployment and orchestration of data and ML pipelines.

Python & SQL Programming
Advanced programming skills in Python and SQL, complemented by experience with Scala and Bash for data engineering and automation tasks.

LLMOps Tooling
Hands-on experience with LLMOps frameworks including LangChain, Qdrant, Langfuse, sentence-transformers, Pydantic and skills/MCP for building and monitoring LLM-based applications.

Data Science Libraries
Extensive use of data science libraries such as pandas, TensorFlow, PyTorch, scikit-learn, and MLflow for model development, feature engineering, A/B testing and calibration.

Probabilistic & Deterministic Forecasting
Experience in establishing probabilistic and deterministic forecasting skill metrics, orchestrating Earth-System-Model simulations, and analysing large data cubes of 40TB+ in atmospheric and climate science contexts.

Scientific Research & Publication
Track record of publishing three peer-reviewed first-author papers in the field of atmospheric science and climate modelling during doctoral research.