I am Nikan Doosti
'Nikan' means all the goodness in the world and it's a Persian-Zoroastrian name, and 'Doosti' literally means friendship! and I always try to live up to my name! 😊

I’m a machine learning researcher, currently working as a first-year PhD student on AI-assisted Product Development, mainly integration of data-driven deep learning in additive manufacturing (metal 3D printing) process.
Before this, as an ML engineer, I utilize artificial intelligence to provide data-driven decision making by repreenting domain experitise as a step-by-step reproducible platform as the context for integration with LLMs (nowadays it's called context engineering). Previously, I did a research internship at Max Planck Institute for Informatics at AIDAM group in Germany 🇩🇪, working on applications of machine learning in digital fabrication, specifically implicit neural representation and surrogate modeling via differentiabe physics-based simulator. Prior to that, I was mainly focused on classic computer vision, specifically digital image processing.

• 🧐 I'm interested in machine learning, deep learning, physics-based simulation, and I'm passionate about researching fully self-supervised end-to-end implicit representations via differentiable modeling especially for inverse problems!
• 👯 I'm looking to collaborate on PyTorch framework. Meet me on official PyTorch forum: PyTorch Discuss
• 💓 I’m always open to collaborate and having a discussion around research, from ideation to dissemination, industry challenges, and even setting up a local server to play Factorio/DoTA2/CS2 and so on!
• 💬 Ask me about anything, but I don't know how much I don't know. but I don't promise the best (most accurate) or the expected (what you might like to hear) response! So don't hesitate to email me.
• 📫 How to reach me: My email nikan [dot] doosti [at] outlook [dot] com (more details on the bottom of home page of my website)
• ⭐ Giving stars is a small gesture, but it means a lot! So give stars to cool projects.

I follow Github timeline almost everyday (Works as a social media for me :D).