Farhad Davaripour, PhD.
As an MLOps developer, simulation specialist, and research engineer with over 6 years of experience, I specialize in developing innovative data-driven solutions. My tenure as a postdoc at NC Inc. was marked by leveraging machine learning and synthetic data from finite element simulations for thermal stress analysis in pipe bends, directly addressing industry challenges. In my current role at Arcurve Inc., I utilize cloud services (e.g., Azure and AWS) to develop/maintain end-to-end machine-learning pipelines. Additionally, my personal project 'DocsGPT,' a RAG-based querying app using LangChain and OpenAI's API, demonstrates my proficiency in implementing solutions using generative AI.
Educational Contents/Apps
2. Next Token Prediction
In this lecture, you will learn how Temperature and Top-P control the randomness in LLM-generated outputs
Dashboard: Link
Distilled Notes
Educational Contents for Pipeline Engineers
AI in Pipeline Engineering
This course explores various machine learning (ML) implementations specifically targeting preventative maintenance in pipeline engineering challenges.
GitHub page: Link
GenAI in Pipeline Engineering
This course explores various advanced GenAI (e.g., ReAct Agentic Workflows) implementations in the field of pipeline engineering.
GitHub page: Link
Applications
CFRP Reinforced Pipe Bend
This project employs machine learning and synthetic dataset to predict the peak equivalent stress imposed on a CFRP-wrapped HDD overbend.
GitHub Page: Link