Panel 2 · Planned certificate · 12 weeks
Certificate in Compute Governance & Model Provenance 2
Frontier Safety Frameworks & Compute Governance
Core syllabus
What you will investigate
- 01
Applied tensor manipulation with einops and einsum
- 02
SVD and low-rank projections
- 03
INT8, FP8, AWQ and GPTQ quantization trade-offs
- 04
Signed Machine Learning Bills of Materials, VRAM checksums and pre-deployment evidence gates
Reproducible evidence
Panel deliverable
Deliver an INT8/FP8 quantized pipeline with automated pre-flight MLBOM signature verification that blocks execution on tampered weights.
AI Control Lab deliverable
Quantize an open-weight model to INT8/FP8, sign an MLBOM manifest, and trigger automated kill-switch/pre-flight halts against tampered weights in the AI Control Lab.
Duration
10 instructional weeks + 2 capstone / defense weeks
Lab
Continuous hands-on work in the AI Control Lab
Assessment
Planned artifact verification and final human sign-off
Stackable by design
Foundational Certificate in AI Assurance & Systems
This panel maps explicitly to the AI Safety & Governance pathway. Panels 1–4 contribute to the 4-panel Foundational milestone; all eight contribute to the 8-panel Advanced Certificate milestone. Certificates can also be pursued individually. Cumulative credentials require the corresponding evidence and human-led defense.
Apply as a StudentUnaccredited institutional credentials; not accredited degrees.