Andrew F.

I'm a senior Data Engineer and AI Engineer with 10+ years of experience building data platforms, production data pipelines, machine learning systems and, more recently, LLM-powered applications. My recent work has focused on building practical AI and data solutions in an enterprise environment, including: • LLM applications and internal knowledge assistants • RAG/chatbot systems over internal documentation • Automated document processing for investment research and legal contracts • Batch and API-based LLM pipelines • Data cataloguing and enrichment using LLMs • Data engineering and ETL/ELT pipelines • Python APIs and backend services • Cloud infrastructure and platform engineering My core stack includes Python, SQL, Snowflake, Databricks, FastAPI, Azure, AWS, Docker and Terraform, with AI/ML experience including OpenAI, Snowflake Cortex, PyTorch and Hugging Face. My background combines software engineering, data engineering and machine learning. Before moving into data platform engineering, I worked in telecoms R&D developing large-scale data pipelines and statistical/ML systems using technologies including Hadoop, Hive, Spark and Python. My research work received the Best Application Paper award at the British Computer Society SGAI conference. I can help with projects such as: • Designing and building production data pipelines • Building LLM/RAG applications around your company's data • Automating document extraction, classification and processing • Developing Python/FastAPI data and AI services • Snowflake and Databricks development • Integrating AI models into existing applications and workflows • Data architecture, database engineering and cloud infrastructure • Taking AI/data prototypes and turning them into maintainable production systems I particularly enjoy projects where the problem isn't simply "build an AI demo", but figuring out how data, software engineering and AI fit together to create something reliable and useful.