hello everyone.
im looking for remote summer/fall internships in fullstack dev, but flexible across roles.
comfortable in working with golang and typescript.
previously worked as a frontend eng at an ai startup.
hey @ namishh . com
resume and gh attached below
Every answer in TextQL now shows its work, inline.
Each citation traces a number back through its entire provenance chain — a visual map of exactly how a number was derived, end to end. This includes which tables were read, the SQL that aggregated them, the Python that reshaped the result, and the answer that came out.
I reverse engineered Qualcomm's NPU compiler to find undocumented behaviour that affects every edge AI deployment.
Things nobody knew:
1. The compiler silently downgrades the precision of your model weights without telling you
2. Memory placement uses HiGHS which is an LP solver (not heuristics)
3. The same model on two different chips with identical reported VTCM can have 33x difference in DDR traffic
4. There's an undocumented internal simulator called Hextimate pricing ops without the hardware
Every NPU vendor be it Qualcomm, MediaTek or Apple NEVER tells you how to make the most use of their hardware.
I was very close to rage quitting before I finally lost all hope and thought of reverse engineering to understand how NPUs are handled.
Read the full write-up below: