Systems & AI engineer focused on low-latency systems programming, edge deep learning inference, and asynchronous LLM pipelines. I build software that spans from bare-metal microcontrollers and POSIX kernel interfaces to distributed web backends.
- 🔭 Current Focus: Edge AI acceleration (INT8 quantization, structural pruning on ARM Cortex) and fault-tolerant distributed edge storage engines.
- 🌱 Diving Deeper Into: Distributed consensus algorithms, low-latency C++20 concurrency primitives, and custom memory allocators.
- 🤝 Open to Collaborate On: High-performance systems programming, edge intelligence, custom OS kernels/schedulers, and scalable asynchronous LLM infrastructure.
- 💬 Ask Me About: C/C++, POSIX threads, memory fragmentation mitigation, edge neural inference (RPi 5 / ESP32), Celery queue architectures, and FreeRTOS.
- ⚡ Fun Fact: I hold patent filings in fail-safe embedded vehicle ignition systems (RTDS) and automated edge histopathology diagnostic hardware (OncoVue).
- Email: taran.wadhawan03@gmail.com
- LinkedIn: linkedin.com/in/taran-wadhawan
- Portfolio: taranwadhawan.github.io/Taran-Wadhawan-Portfolio