Muhammad Afaq Jamshaid

- Contributing to ”Pandapipes”, an open-source Python library for energy pipeline simulation, by resolving bugs during feature migration from the related library ”Pandapower”. - Developed a Plotly + Mapbox module to visualize pipeline networks on real-world maps. - Wrote technical documentation and tutorials to improve onboarding and usage for new developers and users of the library.

- Replaced a manual search process with a machine learning model that predicts valid fuel combinations within a 25×25 dimensional search space containing millions of possibilities. - Delivered a customized end-to-end ML pipeline tailored to the company’s use case, covering dataset creation, model training, prediction, and visualization, achieving 93% accuracy. - Designed a hybrid training strategy for the RL agent by feature-importance feedback and offline learning through injecting data iteratively.

- Benchmarked and evaluated LLM models including ChatGPT, Claude, and LLama against scenario based unittest and pytest cases, assessing compliance with the requirements rubric. - Built supervised fine-tuning datasets and scripts across Python, C++, and JavaScript tasks, generating 1000+ structured prompts and reference responses for SFT and RLHF workflows.