AI Infrastructure

NVIDIA

Hardware debug platforms for next-generation AI/HPC systems.

DFX, scan/JTAG state capture, pre-silicon verification, and debug tooling — focused on making complex silicon observable and repeatable to debug.

Current role

Senior DFX Methodology Engineer, AI Hardware / Silicon Debug Platforms

  • DFX methodology and DFT for AI/HPC silicon platforms (IEEE 1149.1 / 1500 / 1687, JTAG / IJTAG).
  • State capture and observability: scan dump, RAM dump, IO BIST, memory BIST, and DFD flows.
  • Internal scan-debug GUI tooling used across multiple engineering teams.
  • Pre-silicon verification and post-silicon bring-up / debug.
  • DFX security and test-access discipline for complex parts.
  • Cross-team enablement turning low-level silicon behavior into repeatable workflows.

Earlier work

Systems thinking before silicon observability.

2018 – 2024
Intel

DFT feature integration for Intel SoCs, ATE test plans, ATPG/coverage analysis, JTAG/MBIST/scan compression. Drove ~20% scan-efficiency improvement, ~15% test-cost reduction, ~10% coverage gain, and $1M+ annual cost reduction at sub-250 DPPM.

2020 – 2021
Materials & manufacturing

Materials science and manufacturing work underpinning a systems view of reliability — from physical defects to test economics.

2015 – 2021
Education & leadership

Co-Founder of Angelica International School. MS Mechanical Engineering, Northeastern University; BTech Materials Science & Engineering, IIT Kanpur.

Next step

For roles or conversations around AI hardware observability.