Panel 2 · Planned certificate · 12 weeks

Certificate in Compute Governance & Model Provenance 2

Frontier Safety Frameworks & Compute Governance

Core syllabus

What you will investigate

  1. 01

    Applied tensor manipulation with einops and einsum

  2. 02

    SVD and low-rank projections

  3. 03

    INT8, FP8, AWQ and GPTQ quantization trade-offs

  4. 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 Student

Unaccredited institutional credentials; not accredited degrees.