🔭 I’m currently working on
Various applied data science and machine learning projects. Each project is being documented rigorously, and only marked complete once results, methodology, and limitations are clearly written up.

👯 I’m looking to collaborate on
Research-driven ML projects, especially in computer vision, representation learning, and unconventional data modalities (remote sensing, biological data, compressed or noisy signals).

🤝 I’m looking for help with
Peer review and critical feedback on project design, evaluation methodology, and assumptions—particularly from people who are willing to challenge weak reasoning rather than agree politely.

🌱 I’m currently learning
Advanced deep learning techniques, model interpretability, and the theory–practice gap in real-world ML systems. Increasing focus on making models robust rather than just impressive.

💬 Ask me about
Machine learning pipelines, computer vision (including SAR image processing), DNA data storage concepts, facial recognition systems, and practical trade-offs in deploying ML models.

⚡ Fun fact
I care more about whether a model is defensible than whether it gets a slightly higher benchmark score—and I’ll happily discard a clever idea if it doesn’t survive scrutiny.

If you want this tightened further for a GitHub profile or academic bio, that’s a mechanical edit, not a conceptual one.